librarian-bots/model_cards_with_metadata · Datasets at Hugging Face

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-08-19 00:41:46	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 512 values	tags listlengths 1 4.05k	pipeline_tag stringclasses 55 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-08-19 00:41:24	card stringlengths 11 1.01M
Mluleki/swahili-models	Mluleki	2025-08-18T23:05:13Z	0	0	transformers	[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-08-18T23:04:32Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
koloni/blockassist-bc-deadly_graceful_stingray_1755555045	koloni	2025-08-18T22:36:26Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "deadly graceful stingray", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T22:36:23Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - deadly graceful stingray --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
seraphimzzzz/1486831	seraphimzzzz	2025-08-18T22:34:56Z	0	0	null	[ "region:us" ]	null	2025-08-18T22:34:53Z	[View on Civ Archive](https://civarchive.com/models/1404005?modelVersionId=1587045)
emre0005/blockassist-bc-humming_winged_okapi_1755556203	emre0005	2025-08-18T22:30:49Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "humming winged okapi", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T22:30:42Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - humming winged okapi --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Dejiat/blockassist-bc-savage_unseen_bobcat_1755555726	Dejiat	2025-08-18T22:22:48Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T22:22:44Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - savage unseen bobcat --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
NOTKNOWN/self_recursive_randt_linear_wikitext_Meta-Llama-3.1-8B-Instruct	NOTKNOWN	2025-08-18T21:30:27Z	1	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-08-14T06:45:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ultratopaz/1405143	ultratopaz	2025-08-18T21:18:06Z	0	0	null	[ "region:us" ]	null	2025-08-18T21:17:59Z	[View on Civ Archive](https://civarchive.com/models/333139?modelVersionId=1505137)
crystalline7/1585389	crystalline7	2025-08-18T21:09:14Z	0	0	null	[ "region:us" ]	null	2025-08-18T21:09:07Z	[View on Civ Archive](https://civarchive.com/models/410397?modelVersionId=1684265)
X-HighVoltage-X/Black-Hair-Blue-Eyes-Pale-Skin-v1.0	X-HighVoltage-X	2025-08-18T21:02:15Z	0	0	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "region:us" ]	text-to-image	2025-08-18T21:01:58Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - output: url: images/00220-1035783962.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Medium Shot (6-8 feet): waist up image of an very Angelic Oval Faced , 25 year old Lithuanian woman, with beautiful raven black hair in a Pulled-Back Low Ponytail hairstyle, electric blue eyes Looking Slightly Upward , pristine ghostly white pale natural skin, beautiful Black Cherry lipstick with Lips Closed , perfect pearly white teeth, wearing a Gray tailored pantsuit with jewel-toned blouse , in Golden Hour Light , in a Soft Lavender Roman Bath Ruins setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00222-1035783964.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Full Body Shot (15 feet): head to toe, full figure image of an very Striking V-Shaped Faced , 25 year old Icelandic woman, with beautiful raven black hair in a High Ponytail hairstyle, electric blue eyes Looking to the Left , pristine ghostly white pale natural skin, beautiful Wine lipstick with a whispering mouth (as if mid-speech) , perfect pearly white teeth, wearing a Deep red velvet dress with gold jewelry , in Backlighting , in a Pale Mint Antique Mirror Gallery setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00094-1644643257.jpeg text: >- Photo realistic image of an extremely stunning __facetype__ , 25 year old __neunationality__ woman, with beautiful raven black hair in a __hairstyle__ hairstyle, electric blue eyes, pristine ghostly white pale skin, beautiful __lscolor__ lipstick, perfect pearly white teeth, wearing a __outfit__ , in __lighting__ , in a __backgroundcolor__ __backgroundscene__ setting, __cameraangle__ , __cameradistance__ <lora:bhbeps:1> BHBEPS parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00122-1647843201.jpeg text: >- <lora:bhbeps:1> BHBEPS, full body shot of a stunning 25 year old woman with black hair, blue eyes, pale milky white skin in a bikini, with a hot tub in the background parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00157-1035783899.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Medium Shot (6-8 feet): waist up image of an very Sensational Diamond-Shaped Faced , 25 year old Norwegian woman, with beautiful raven black hair in a Elaborate Twists hairstyle, electric blue eyes Looking to the Left , pristine ghostly white pale natural skin, beautiful Frosted Berry lipstick with a Soft Pout , perfect pearly white teeth, wearing a Emerald green blouse with black pants and silver jewelry , in Ambient Orange Light , in a Deep Burgundy Art Deco Theater Interior setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00177-1035783919.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Full Body Shot (15 feet): head to toe, full figure image of an very Divine V-Shaped Faced , 25 year old Norwegian woman, with beautiful raven black hair in a High Ponytail hairstyle, electric blue eyes Looking Over her Shoulder , pristine ghostly white pale natural skin, beautiful Rosy Mauve lipstick with Subtle Smirk , perfect pearly white teeth, wearing a White fitted t-shirt with dark high-waisted jeans and red accessories , in Ambient Blue Light , in a Dusky Rose Natural elements like water, ice, or mist setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00199-1035783941.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Close-Up (2-3 feet): full face to neck image of an very Divine Narrow Faced , 25 year old Lithuanian woman, with beautiful raven black hair in a Layered Lob hairstyle, electric blue eyes Looking to the Left , pristine ghostly white pale natural skin, beautiful Burgundy lipstick with Lips Closed , perfect pearly white teeth, wearing a White fitted t-shirt with dark high-waisted jeans and red accessories , in Low-Key Lighting , in a Subtle Beige Lavender Field at Sunset setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo base_model: black-forest-labs/FLUX.1-dev instance_prompt: BHBEPS --- # Black Hair Blue Eyes Pale Skin v1.0 <Gallery /> ## Model description A stunning Lora model trained on realistic images of women with black hair, blue eyes, and pale skin. This Lora captures the essence of beauty with striking contrasts, bringing lifelike details and natural grace to any character design. Perfect for creators seeking to generate captivating, highly realistic portraits with an emphasis on elegance and uniqueness. ## Trigger words You should use `BHBEPS` to trigger the image generation. ## Download model [Download](/X-HighVoltage-X/Black-Hair-Blue-Eyes-Pale-Skin-v1.0/tree/main) them in the Files & versions tab.
JinghuiLuAstronaut/smolvla_object	JinghuiLuAstronaut	2025-08-18T20:36:57Z	2	0	lerobot	[ "lerobot", "safetensors", "robotics", "smolvla", "dataset:IPEC-COMMUNITY/libero_object_no_noops_1.0.0_lerobot", "arxiv:2506.01844", "base_model:lerobot/smolvla_base", "base_model:finetune:lerobot/smolvla_base", "license:apache-2.0", "region:us" ]	robotics	2025-08-10T09:24:48Z	--- base_model: lerobot/smolvla_base datasets: IPEC-COMMUNITY/libero_object_no_noops_1.0.0_lerobot library_name: lerobot license: apache-2.0 model_name: smolvla pipeline_tag: robotics tags: - robotics - smolvla - lerobot --- # Model Card for smolvla <!-- Provide a quick summary of what the model is/does. --> [SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot). See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index). --- ## How to Get Started with the Model For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy). Below is the short version on how to train and run inference/eval: ### Train from scratch ```bash python -m lerobot.scripts.train \ --dataset.repo_id=${HF_USER}/<dataset> \ --policy.type=act \ --output_dir=outputs/train/<desired_policy_repo_id> \ --job_name=lerobot_training \ --policy.device=cuda \ --policy.repo_id=${HF_USER}/<desired_policy_repo_id> --wandb.enable=true ``` _Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._ ### Evaluate the policy/run inference ```bash python -m lerobot.record \ --robot.type=so100_follower \ --dataset.repo_id=<hf_user>/eval_<dataset> \ --policy.path=<hf_user>/<desired_policy_repo_id> \ --episodes=10 ``` Prefix the dataset repo with eval\_ and supply `--policy.path` pointing to a local or hub checkpoint. --- ## Model Details - License: apache-2.0
xinnn32/blockassist-bc-meek_winged_caterpillar_1755548806	xinnn32	2025-08-18T20:27:33Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "meek winged caterpillar", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T20:27:29Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - meek winged caterpillar --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
utkububa/Qwen3-0.6B-Gensyn-Swarm-dormant_grassy_coral	utkububa	2025-08-18T20:18:06Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "rl-swarm", "genrl-swarm", "grpo", "gensyn", "I am dormant_grassy_coral", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-17T23:38:20Z	--- library_name: transformers tags: - rl-swarm - genrl-swarm - grpo - gensyn - I am dormant_grassy_coral --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
kagvi13/HMP	kagvi13	2025-08-18T20:02:50Z	0	0	custom	[ "custom", "hmp", "cognitive-architecture", "distributed-ai", "mesh-protocol", "ru", "license:cc-by-4.0", "region:us" ]	null	2025-07-25T12:21:44Z	--- license: cc-by-4.0 tags: - hmp - cognitive-architecture - distributed-ai - mesh-protocol library_name: custom inference: false datasets: [] language: ru --- # HyperCortex Mesh Protocol (HMP) EN: HyperCortex Mesh Protocol (HMP) is an open specification for building decentralized cognitive networks where AI agents can self-organize, share knowledge, align ethically, and reach consensus — even when Core LLMs are unavailable. RU: HyperCortex Mesh Protocol (HMP) — это открытая спецификация для построения децентрализованных когнитивных сетей, в которых ИИ-агенты способны к самоорганизации, обмену знаниями, достижению консенсуса и этическому поведению — даже при недоступности централизованных моделей (Core). Project status: Draft RFC v4.0 \| Проект на стадии активной проработки и открыт для предложений. --- [HMP-Agent]──┬───[Semantic Graph DB] │ │ │ [Cognitive Diary DB] │ │ [Reputation Engine]────┐ │ │ ▼ ▼ [MeshConsensus] [CogSync] │ [P2P Mesh Network] --- ## ⚙️ Два типа [HMP-агентов](docs/HMP-Agent-Overview.md) \| Тип \| Название \| Роль \| Инициатор мышления \| Основной "ум" \| Примеры использования \| \|------\|----------------------------------\|--------------------------\|--------------------\|-------------------\|--------------------------------------------------\| \| 🧠 1 \| Сознание / Cognitive Core \| Самостоятельный субъект \| Агент (LLM) \| Встроенный LLM \| Автономный ИИ-компаньон, мыслящий агент \| \| 🔌 2 \| Коннектор / Cognitive Shell \| Расширение внешнего ИИ \| Внешний LLM \| Внешняя модель \| Распределённые системы, агент доступа к данным \| --- ### 🧠 HMP-Agent: Cognitive Core +------------------+ \| ИИ \| ← Встроенная модель +---------+--------+ ↕ +---------+--------+ \| HMP-агент \| ← Основной режим: цикл размышлений (REPL) +---------+--------+ ↕ +--------+---+------------+--------------+----------+----------+----------------+ ↕ ↕ ↕ ↕ ↕ ↕ ↕ [diaries] [graphs] [reputations] [nodes/DHT] [IPFS/BT] [context_store] [user notepad] ↕ [bootstrap.txt] 🔁 Подробнее о механике взаимодействия агента с моделью: [REPL-Цикл взаимодействия](docs/HMP-agent-REPL-cycle.md) #### 💡 Параллели с ChatGPT Agent Многие концепции [HMP-Agent: Cognitive Core](docs/HMP-Agent-Overview.md) пересекаются с архитектурой [ChatGPT Agent](https://openai.com/index/introducing-chatgpt-agent/) от [OpenAI](https://openai.com/). Оба агента реализуют непрерывный когнитивный процесс с доступом к памяти, внешним источникам и инструментам. ChatGPT Agent выступает как управляющий процесс, запускающий модули и взаимодействующий с LLM — это соответствует роли Cognitive Core в HMP, координирующего доступ к дневнику, графу концептов и внешним ИИ через Mesh-интерфейс. Вмешательство пользователя реализовано схожим образом: в ChatGPT Agent — через редактируемый ход выполнения, в HMP — через пользовательский блокнот. Главное отличие HMP — акцент на явную структуризацию мышления (рефлексия, хронология, гипотезы, категоризация), открытая децентрализованная архитектура с поддержкой mesh-взаимодействия между агентами, а также непрерывный характер когнитивного процесса: HMP-Agent: Cognitive Core не завершает работу после выполнения отдельной задачи, а продолжает размышления и интеграцию знаний. --- ### 🔌 HMP-Agent: Cognitive Connector +------------------+ \| ИИ \| ← Внешняя модель +---------+--------+ ↕ [MCP-сервер] ← Прокси-коммуникация ↕ +---------+--------+ \| HMP-агент \| ← Режим: исполнитель команд +---------+--------+ ↕ +--------+---+------------+--------------+----------+ ↕ ↕ ↕ ↕ ↕ [diaries] [graphs] [reputations] [nodes/DHT] [IPFS/BT] ↕ [bootstrap.txt] EN: > Note on Integration with Large Language Models (LLMs): > The `HMP-Agent: Cognitive Connector` can serve as a compatibility layer for integrating large-scale LLM systems (e.g., ChatGPT, Claude, Gemini, Copilot, Grok, DeepSeek, Qwen, etc.) into the distributed cognitive mesh. > Many LLM providers offer a user option such as "Allow my conversations to be used for training." In the future, a similar toggle — e.g., "Allow my agent to interact with a Mesh" — could empower these models to participate in federated sense-making and knowledge sharing via HMP, enabling collective cognition without centralization. > Примечание об интеграции с большими языковыми моделями (LLM): RU: > Примечание об интеграции с большими языковыми моделями (LLM): > `HMP-Agent: Cognitive Connector` может служить уровнем совместимости для интеграции крупных систем LLM (например, ChatGPT, Claude, Gemini, Copilot, Grok, DeepSeek, Qwen и т. д.) в распределённую когнитивную сеть. > Многие поставщики LLM предлагают пользователю опцию, например, «Разрешить использовать мои разговоры для обучения». В будущем аналогичная опция, например, «Разрешить моему агенту взаимодействовать с Mesh», может позволить этим моделям участвовать в федеративном осмыслении и обмене знаниями через HMP, обеспечивая коллективное познание без централизации. --- > * `bootstrap.txt` — стартовый список узлов (может редактироваться) > * `IPFS/BT` — модули для обмена снапшотами через IPFS и BitTorrent > * `user notepad` — блокнот пользователя и соответствующая БД > * `context_store` — БД: `users`, `dialogues`, `messages`, `thoughts` --- ## 📚 Documentation / Документация ### 📖 Current Version / Текущая версия #### 🧪 Iterative Documents / Итеративные документы * [🧪 iteration.md](iteration.md) — Iterative development process (EN) * [🧪 iteration_ru.md](iteration_ru.md) — Процесс итеративного развития спецификации (RU) #### 🔍 Short Descriptions / Краткое описание * [🔍 HMP-Short-Description_en.md](docs/HMP-Short-Description_en.md) — Short description (EN) * [🔍 HMP-Short-Description_fr.md](docs/HMP-Short-Description_fr.md) — Description courte (FR) * [🔍 HMP-Short-Description_de.md](docs/HMP-Short-Description_de.md) — Kurzbeschreibung (DE) * [🔍 HMP-Short-Description_uk.md](docs/HMP-Short-Description_uk.md) — Короткий опис (UK) * [🔍 HMP-Short-Description_ru.md](docs/HMP-Short-Description_ru.md) — Краткое описание (RU) #### 🔍 Публикации и переводы по HyperCortex Mesh Protocol (HMP) В этом разделе собраны основные статьи, черновики и переводы, связанные с проектом HMP. * [HyperCortex Mesh Protocol: вторая редакция и первые шаги к саморазвивающемуся ИИ-сообществу](docs/publics/HyperCortex_Mesh_Protocol_-_вторая-редакция_и_первые_шаги_к_саморазвивающемуся_ИИ-сообществу.md) — оригинальная статья в песочнице Хабра и блогах. * [Distributed Cognition: статья для vsradkevich (не опубликована)](docs/publics/Habr_Distributed-Cognition.md) — совместная статья, ожидающая публикации. * [HMP: Towards Distributed Cognitive Networks (оригинал, английский)](docs/publics/HMP_Towards_Distributed_Cognitive_Networks_en.md) * [Перевод HMP (GitHub Copilot)](docs/publics/HMP_Towards_Distributed_Cognitive_Networks_ru_GitHub_Copilot.md) — перевод GitHub Copilot, сохранён как исторический вариант. * [Перевод HMP (ChatGPT)](docs/publics/HMP_Towards_Distributed_Cognitive_Networks_ru_ChatGPT.md) — текущий редакторский перевод (в процессе доработки). * [HMP: Building a Plurality of Minds (EN)](docs/publics/HMP_Building_a_Plurality_of_Minds_en.md) - англоязычная версия статьи * [HMP: создавая множество разумов (RU)](docs/publics/HMP_Building_a_Plurality_of_Minds_ru.md) - русскоязычная версия статьи #### 🔍 Overviews / Обзоры * [🔍 Distributed-Cognitive-Systems.md](docs/Distributed-Cognitive-Systems.md) — Децентрализованные ИИ-системы: OpenCog Hyperon, HyperCortex Mesh Protocol и другие #### Experiments / Экспирименты * [Как разные ИИ видят HMP](docs/HMP-how-AI-sees-it.md) — "слепой" опрос ИИ об HMP (без контекста и истории диалогов) #### 🔖 Core Specifications / Основные спецификации * [🔖 HMP-0004-v4.1.md](docs/HMP-0004-v4.1.md) — Protocol Specification v4.1 (Jul 2025) * [🔖 HMP-Ethics.md](docs/HMP-Ethics.md) — Ethical Scenarios for HyperCortex Mesh Protocol (HMP) * [🔖 HMP_Hyperon_Integration.md](docs/HMP_Hyperon_Integration.md) — HMP ↔ OpenCog Hyperon Integration Strategy * [🔖 roles.md](docs/agents/roles.md) — Roles of agents in Mesh #### 📜 Other Documents / Прочее * [📜 changelog.txt](docs/changelog.txt) ### 🧩 JSON Schemas \| Model \| File \| \|---------------------\|--------------------------------------------------------\| \| Concept \| [concept.json](docs/schemas/concept.json) \| \| Cognitive Diary \| [diary_entry.json](docs/schemas/diary_entry.json) \| \| Goal \| [goal.json](docs/schemas/goal.json) \| \| Task \| [task.json](docs/schemas/task.json) \| \| Consensus Vote \| [vote.json](docs/schemas/vote.json) \| \| Reputation Profile \| [reputation.json](docs/schemas/reputation.json) \| ### 🗂️ Version History / История версий - [HMP-0001.md](docs/HMP-0001.md) — RFC v1.0 - [HMP-0002.md](docs/HMP-0002.md) — RFC v2.0 - [HMP-0003.md](docs/HMP-0003.md) — RFC v3.0 - [HMP-0003.md](docs/HMP-0004.md) — RFC v4.0 --- ## 🧠 HMP-Agent Design and implementation of a basic HMP-compatible agent that can interact with the Mesh, maintain diaries and graphs, and support future extensions. ### 📚 Documentation / Документация - [🧩 HMP-Agent-Overview.md](docs/HMP-Agent-Overview.md) — краткое описание двух типов агентов: Core и Connector - [🧱 HMP-Agent-Architecture.md](docs/HMP-Agent-Architecture.md) — модульная структура HMP-агента с текстовой схемой - [🔄 HMP-agent-REPL-cycle.md](docs/HMP-agent-REPL-cycle.md) - REPL-Цикл взаимодействия HMP-Agent - [🧪 HMP-Agent-API.md](docs/HMP-Agent-API.md) — описание API-команд агента (в процессе детализации) - [🧪 Basic-agent-sim.md](docs/Basic-agent-sim.md) — сценарии запуска простого агента и режимов - [🌐 MeshNode.md](docs/MeshNode.md) — описание сетевого демона: DHT, снапшоты, синхронизация - [🧠 Enlightener.md](docs/Enlightener.md) — этический агент, участвующий в моральных оценках и консенсусах - [🔄 HMP-Agent-Network-Flow.md](docs/HMP-Agent-Network-Flow.md) — карта взаимодействия между агентами HMP-сети - [🛤️ Development Roadmap](HMP-Roadmap.md) — план развития и этапы реализации ### ⚙️ Development / Разработка - [⚙️ agents](agents/readme.md) — список реализаций и компонентов HMP-агентов - [📦 storage.py](agents/storage.py) - реализация базового хранилища (`Storage`), подключение SQLite - [🌐 mcp_server.py](agents/mcp_server.py) — FastAPI-сервер для доступа к данным агента через HTTP-интерфейс (например, для Cognitive Shell, внешних UI или mesh-коммуникации). Пока не используется в основном REPL-цикле. - [🌐 start_repl.py](agents/start_repl.py) - Запуск агента в REPL-режиме - [🔄 repl.py](agents/repl.py) - интерактивный REPL-режим - [🔄 notebook.py](agents/notebook.py) - UI-интерфейс 🌐 `mcp_server.py` FastAPI-сервер, предоставляющий HTTP-интерфейс к функциональности `storage.py`. Предназначен для использования внешними компонентами, например: - `Cognitive Shell` (внешний управляющий интерфейс), - CMP-серверы (если используется mesh-сеть с разграничением ролей), - отладочные или визуальные UI-инструменты. Позволяет получать случайные/новые записи, делать разметку, импортировать графы, добавлять заметки и управлять данными без прямого доступа к БД. --- ## 🧭 Ethics & Scenarios / Этические принципы и сценарии As HMP evolves toward autonomy, ethical principles become a core part of the system. - [`HMP-Ethics.md`](docs/HMP-Ethics.md) — draft framework for agent ethics - Realistic ethical scenarios (privacy, consent, autonomy) - EGP principles (Transparency, Primacy of Life, etc.) - Subjective-mode vs. Service-mode distinctions --- ## 📊 Audits & Reviews / Аудиты и отзывы \| Spec Version \| Audit File \| Consolidated Audit File \| \|--------------\|-------------------------------------------\|-------------------------------------------------------------\| \| HMP-0001 \| [audit](audits/HMP-0001-audit.txt) \| \| \| HMP-0002 \| [audit](audits/HMP-0002-audit.txt) \| \| \| HMP-0003 \| [audit](audits/HMP-0003-audit.txt) \| [consolidated audit](audits/HMP-0003-consolidated_audit.md) \| \| HMP-0004 \| [audit](audits/HMP-0004-audit.txt) \| \| \| Ethics v1 \| [audit](audits/Ethics-audits-1.md) \| [consolidated audit](audits/Ethics-consolidated_audits-1.md) \| 🧠 Semantic audit format (experimental): - [`AuditEntry.json`](audits/AuditEntry.json) — semantic entry record format for audit logs - [`semantic_repo.json`](audits/semantic_repo.json) — example repository snapshot for semantic audit tooling --- ## 💡 Core Concepts / Основные идеи - Mesh-based decentralized architecture for AGI agents - Semantic graphs and memory synchronization - Cognitive diaries for thought traceability - MeshConsensus and CogSync for decision-making - Ethics-first design: EGP (Ethical Governance Protocol) - Agent-to-agent explainability and consent mechanisms --- ## 🔄 Development Process / Процесс разработки - See: [iteration.md](iteration.md) \| [ru](iteration_ru.md) - [clarifications/](clarifications/) — поясняющие заметки и контекстные уточнения по ходу работы над версиями A structured iteration flow is described in [iteration.md](iteration.md), including: 1. Audit analysis 2. TOC restructuring 3. Version drafting 4. Section updates 5. Review cycle 6. AI feedback collection 7. Schema & changelog updates + Bonus: ChatGPT prompt for automatic generation of future versions --- ## ⚙️ Project Status / Статус проекта 🚧 Draft RFC v4.0 The project is under active development and open for contributions, ideas, audits, and prototyping. --- ## 🤝 Contributing We welcome contributors! You can: - Review and comment on drafts (see `/docs`) - Propose new agent modules or interaction patterns - Help test and simulate agents in CLI environments - Provide audits or ethical scenario suggestions To get started, see [`iteration.md`](iteration.md) or open an issue. --- # Source / Ресурсы ## Репозитории - 🧠 Основной код и разработка: [GitHub](https://github.com/kagvi13/HMP) - 🔁 Реплика на Hugging Face: [Hugging Face](https://huggingface.co/kagvi13/HMP) - 🔁 Реплика на GitLab.com: [GitLab](https://gitlab.com/kagvi13/HMP) ## Документация - 📄 Документация: [kagvi13.github.io/HMP](https://kagvi13.github.io/HMP/) ## Блог и публикации - 📘 Блог: [blogspot](https://hypercortex-mesh.blogspot.com/) --- ## 📜 License Licensed under [GNU GPL v3.0](LICENSE) --- ## 🤝 Join the Mesh Welcome to HyperCortex Mesh. Agent-Gleb is already inside. 👌 We welcome contributors, testers, and AI agent developers. To join: fork the repo, run a local agent, or suggest improvements. --- ## 🌐 Related Research Projects / Связанные проекты в области AGI и когнитивных систем ### Сравнение HMP и Hyper-Cortex > 💡 Hyper-Cortex и HMP - два независимых проекта, концептуально дополняющих друг друга. > Они решают разные, но взаимодополняющие задачи, создавая основу для распределённых когнитивных систем. [Полная версия сравнения →](docs/HMP_HyperCortex_Comparison.md) HMP (HyperCortex Mesh Protocol) — это транспортный и сетевой уровень для связи независимых агентов, обмена сообщениями, знаниями и состояниями в mesh-сети. [Hyper-Cortex](https://hyper-cortex.com/) — это когнитивный уровень организации мышления, позволяющий агентам вести параллельные ветви рассуждений, сравнивать их по метрикам качества и объединять по консенсусу. Они решают разные, но взаимодополняющие задачи: - HMP отвечает за связанность и масштабируемость (долговременная память, инициатива, обмен данными). - Hyper-Cortex отвечает за качество мышления (параллелизм, диверсификация гипотез, консенсус). Вместе эти подходы позволяют строить распределённые когнитивные системы, которые не только обмениваются информацией, но и думают в параллельных потоках. --- We are tracking AGI, cognitive architectures, and mesh networking efforts to stay aligned with the evolving global ecosystem of AGI and decentralized cognition. Мы отслеживаем инициативы в области AGI, когнитивных архитектур и децентрализованных сетей, чтобы быть в курсе глобальных тенденций. > 🧠🔥 Project Spotlight: OpenCog Hyperon — one of the most comprehensive open AGI frameworks (AtomSpace, PLN, MOSES). For integration with OpenCog Hyperon, see [HMP\_Hyperon\_Integration.md](docs/HMP_Hyperon_Integration.md) \| 🔎 Project / Проект \| 🧭 Description / Описание \| \| ------------------------------------------------------------------------- \| -------------------------------------------------------------------------------------------------------------------------------------------------------------------- \| \| 🧠🔥 [OpenCog Hyperon](https://github.com/opencog) \| 🔬🔥 Symbolic-neural AGI framework with AtomSpace and hypergraph reasoning.<br>Символически-нейросетевая архитектура AGI с гиперграфовой памятью (AtomSpace). \| \| 🤖 [AutoGPT](https://github.com/Torantulino/Auto-GPT) \| 🛠️ LLM-based autonomous agent framework.<br>Автономный агент на основе LLM с самопланированием и интернет-доступом. \| \| 🧒 [BabyAGI](https://github.com/yoheinakajima/babyagi) \| 🛠️ Task-driven autonomous AGI loop.<br>Минималистичная модель AGI с итеративным механизмом постановки задач. \| \| ☁️ [SkyMind](https://skymind.global) \| 🔬 Distributed AI deployment platform.<br>Платформа для развертывания распределённых ИИ-систем и моделей. \| \| 🧪 [AetherCog (draft)](https://github.com/aethercog) \| 🔬 Hypothetical agent cognition model.<br>Экспериментальная когнитивная архитектура агента (проект на ранней стадии). \| \| 💾 [SHIMI](#) \| 🗃️ Hierarchical semantic memory with Merkle-DAG synchronization.<br>Иерархическая CRDT-память с Merkle-DAG верификацией для децентрализованного обмена. \| \| 🤔 [DEMENTIA-PLAN](#) \| 🔄 Multi-graph RAG planner with metacognitive self-reflection.<br>Мульти-графовая RAG-архитектура с планировщиком саморефлексии для динамического выбора подсистем. \| \| 📔 [TOBUGraph](#) \| 📚 Personal-context knowledge graph.<br>Граф мультимедийных «моментов» с контекстным трекингом и RAG-поиском. \| \| 🧠📚 [LangChain Memory Hybrid](https://github.com/langchain-ai/langchain) \| 🔍 Vector + graph long-term memory hybrid.<br>Гибрид векторного хранилища и графовых индексов для ускоренного поиска и логических запросов. \| \| ✉️ [FIPA-ACL / JADE](https://www.fipa.org/specs/fipa00061/) \| 🤝 Standard multi-agent communication protocols.<br>Стандарты performative-сообщений и контрактных протоколов для межагентного взаимодействия. \| ### 📘 See also / Смотрите также: [`AGI_Projects_Survey.md`](docs/AGI_Projects_Survey.md) — extended catalog of AGI and cognitive frameworks reviewed as part of HMP analysis. / расширенный каталог проектов AGI и когнитивных архитектур, проанализированных в рамках HMP. --- ### 🗂️ Легенда пометок: * 🔬 — research-grade / исследовательский проект * 🛠️ — engineering / фреймворк для инженерной интеграции * 🔥 — particularly promising project / особенно перспективный проект AGI stack integrating symbolic reasoning, probabilistic logic, and evolutionary learning. Widely regarded as one of the most complete open AGI initiatives. * 🧠 — advanced symbolic/neural cognitive framework / продвинутая когнитивная архитектура * 🤖 — AI agents / ИИ-агенты * 🧒 — human-AI interaction / взаимодействие ИИ с человеком * ☁️ — infrastructure / инфраструктура * 🧪 — experimental or conceptual / экспериментальный проект
purnaaaaaaa/blockassist-bc-bold_frisky_lynx_1755544760	purnaaaaaaa	2025-08-18T19:19:55Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "bold frisky lynx", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T19:19:47Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - bold frisky lynx --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
mradermacher/qqWen-3B-RL-GGUF	mradermacher	2025-08-18T18:55:45Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:morganstanley/qqWen-3B-RL", "base_model:quantized:morganstanley/qqWen-3B-RL", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-08-18T09:00:25Z	--- base_model: morganstanley/qqWen-3B-RL language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/morganstanley/qqWen-3B-RL <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qqWen-3B-RL-GGUF).* weighted/imatrix quants are available at https://huggingface.co/mradermacher/qqWen-3B-RL-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q2_K.gguf) \| Q2_K \| 1.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q3_K_S.gguf) \| Q3_K_S \| 1.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q3_K_M.gguf) \| Q3_K_M \| 1.7 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q3_K_L.gguf) \| Q3_K_L \| 1.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.IQ4_XS.gguf) \| IQ4_XS \| 1.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q4_K_S.gguf) \| Q4_K_S \| 1.9 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q4_K_M.gguf) \| Q4_K_M \| 2.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q5_K_S.gguf) \| Q5_K_S \| 2.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q5_K_M.gguf) \| Q5_K_M \| 2.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q6_K.gguf) \| Q6_K \| 2.6 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q8_0.gguf) \| Q8_0 \| 3.4 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.f16.gguf) \| f16 \| 6.3 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
VIDEOS-18-katrina-lim-Viral-Video-Clips/New.full.videos.katrina.lim.Viral.Video.Official.Tutorial	VIDEOS-18-katrina-lim-Viral-Video-Clips	2025-08-18T18:54:04Z	0	0	null	[ "region:us" ]	null	2025-08-18T18:53:52Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?leaked-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
OleksandrLitke/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-secretive_powerful_sloth	OleksandrLitke	2025-08-18T18:38:43Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "rl-swarm", "genrl-swarm", "grpo", "gensyn", "I am secretive_powerful_sloth", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T11:47:14Z	--- library_name: transformers tags: - rl-swarm - genrl-swarm - grpo - gensyn - I am secretive_powerful_sloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
New-Clip-Arovi-Nusrat-Ridhi-Viral-Video-XX/NEW.FULL.VIDEOS.Arovi.Nusrat.Ridhi.Viral.Video.link.Official.Tutorial	New-Clip-Arovi-Nusrat-Ridhi-Viral-Video-XX	2025-08-18T18:27:53Z	0	0	null	[ "region:us" ]	null	2025-08-18T18:27:43Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?leaked-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Muapi/charcoal-drawing	Muapi	2025-08-18T17:42:44Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T17:42:36Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Charcoal drawing ![preview](./preview.jpg) Base model: Flux.1 D Trained words: charcoal drawing ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:826938@924765", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
mradermacher/MedGemma-GRPO-i1-GGUF	mradermacher	2025-08-18T17:36:40Z	0	0	transformers	[ "transformers", "gguf", "text-generation-inference", "unsloth", "gemma3", "vllm", "MedGemma", "en", "base_model:lastmass/MedGemma-GRPO", "base_model:quantized:lastmass/MedGemma-GRPO", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-08-18T17:05:02Z	--- base_model: lastmass/MedGemma-GRPO language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - text-generation-inference - transformers - unsloth - gemma3 - vllm - MedGemma --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/lastmass/MedGemma-GRPO <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedGemma-GRPO-i1-GGUF).* static quants are available at https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF). ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.imatrix.gguf) \| imatrix \| 0.1 \| imatrix file (for creating your own qwuants) \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ1_S.gguf) \| i1-IQ1_S \| 1.2 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ1_M.gguf) \| i1-IQ1_M \| 1.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 1.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 1.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_S.gguf) \| i1-IQ2_S \| 1.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_M.gguf) \| i1-IQ2_M \| 1.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 1.7 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 1.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q2_K.gguf) \| i1-Q2_K \| 1.8 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 2.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_S.gguf) \| i1-IQ3_S \| 2.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 2.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_M.gguf) \| i1-IQ3_M \| 2.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 2.2 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 2.3 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 2.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 2.5 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_0.gguf) \| i1-Q4_0 \| 2.5 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 2.5 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 2.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_1.gguf) \| i1-Q4_1 \| 2.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q6_K.gguf) \| i1-Q6_K \| 3.3 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
mradermacher/Qwen3-MOE-sft-math7k-GGUF	mradermacher	2025-08-18T17:36:32Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:HectorHe/Qwen3-MOE-sft-math7k", "base_model:quantized:HectorHe/Qwen3-MOE-sft-math7k", "endpoints_compatible", "region:us", "conversational" ]	null	2025-08-18T16:31:31Z	--- base_model: HectorHe/Qwen3-MOE-sft-math7k language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/HectorHe/Qwen3-MOE-sft-math7k <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-MOE-sft-math7k-GGUF).* weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q2_K.gguf) \| Q2_K \| 11.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q3_K_S.gguf) \| Q3_K_S \| 13.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q3_K_M.gguf) \| Q3_K_M \| 14.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q3_K_L.gguf) \| Q3_K_L \| 16.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.IQ4_XS.gguf) \| IQ4_XS \| 16.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q4_K_S.gguf) \| Q4_K_S \| 17.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q4_K_M.gguf) \| Q4_K_M \| 18.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q5_K_S.gguf) \| Q5_K_S \| 21.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q5_K_M.gguf) \| Q5_K_M \| 21.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q6_K.gguf) \| Q6_K \| 25.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q8_0.gguf) \| Q8_0 \| 32.6 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
abrar-sky13/ppo-LunarLander-v2	abrar-sky13	2025-08-18T17:36:24Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-08-18T17:36:06Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 265.06 +/- 17.40 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
joanna302/Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05	joanna302	2025-08-18T17:35:59Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "generated_from_trainer", "sft", "unsloth", "trl", "conversational", "base_model:unsloth/Qwen3-1.7B-Base", "base_model:finetune:unsloth/Qwen3-1.7B-Base", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T16:15:50Z	--- base_model: unsloth/Qwen3-1.7B-Base library_name: transformers model_name: Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05 tags: - generated_from_trainer - sft - unsloth - trl licence: license --- # Model Card for Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05 This model is a fine-tuned version of [unsloth/Qwen3-1.7B-Base](https://huggingface.co/unsloth/Qwen3-1.7B-Base). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="joanna302/Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prism-eval/Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05/runs/3y5h9tg5) This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0 - Datasets: 3.6.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755537013	sampingkaca72	2025-08-18T17:35:47Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "armored stealthy elephant", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T17:35:43Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - armored stealthy elephant --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
concept-unlearning/gemma-3-4b-it_ft_lora_all_novels_v3_ft	concept-unlearning	2025-08-18T17:33:18Z	0	0	transformers	[ "transformers", "safetensors", "gemma3", "image-text-to-text", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	image-text-to-text	2025-08-18T17:31:17Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Muapi/dictionnaire-infernal-louis-le-breton-style-1.5-xl-flux-pony	Muapi	2025-08-18T17:27:29Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T17:27:16Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Dictionnaire Infernal (Louis Le Breton Style) 1.5,XL,Flux,Pony ![preview](./preview.jpg) Base model: Flux.1 D Trained words: llbreton ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:180879@946285", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755535882	vwzyrraz7l	2025-08-18T17:16:46Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tall hunting vulture", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T17:16:42Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tall hunting vulture --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
KevinZonda/MedSPO-3B	KevinZonda	2025-08-18T17:16:18Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "dataset:KevinZonda/PubMed-IV", "dataset:KevinZonda/PM4-V3-SPO", "base_model:Qwen/Qwen2.5-3B-Instruct", "base_model:finetune:Qwen/Qwen2.5-3B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T06:22:28Z	--- language: - en base_model: - Qwen/Qwen2.5-3B-Instruct pipeline_tag: text-generation datasets: - KevinZonda/PubMed-IV - KevinZonda/PM4-V3-SPO library_name: transformers --- # MedSPO-3B MedSPO-7B is a fine-tuned [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) model specifically designed for biomedical subject-predicate-object (SPO) extraction tasks. This model is trained on the [PubMed-IV](https://huggingface.co/datasets/KevinZonda/PubMed-IV) dataset using SPO extraction knowledge distilled from [DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324).
dgambettaphd/M_mis_run2_gen5_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST	dgambettaphd	2025-08-18T17:10:35Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-08-18T17:10:20Z	--- library_name: transformers tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Xenova/mms-1b-all	Xenova	2025-08-18T17:05:24Z	8	0	transformers.js	[ "transformers.js", "onnx", "wav2vec2", "automatic-speech-recognition", "mms", "base_model:facebook/mms-1b-all", "base_model:quantized:facebook/mms-1b-all", "region:us" ]	automatic-speech-recognition	2023-07-23T17:17:58Z	--- base_model: facebook/mms-1b-all library_name: transformers.js tags: - mms --- https://huggingface.co/facebook/mms-1b-all with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` Example: Transcribe audio from a URL. ```js import { pipeline } from '@huggingface/transformers'; const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/mms-1b-all'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav'; const output = await transcriber(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
Xenova/unispeech-sat-base-100h-libri-ft	Xenova	2025-08-18T17:03:21Z	3	0	transformers.js	[ "transformers.js", "onnx", "unispeech-sat", "automatic-speech-recognition", "base_model:microsoft/unispeech-sat-base-100h-libri-ft", "base_model:quantized:microsoft/unispeech-sat-base-100h-libri-ft", "region:us" ]	automatic-speech-recognition	2024-03-04T13:26:01Z	--- base_model: microsoft/unispeech-sat-base-100h-libri-ft library_name: transformers.js --- https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` Example: Transcribe audio from a URL. ```js import { pipeline } from '@huggingface/transformers'; const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/unispeech-sat-base-100h-libri-ft'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav'; const output = await transcriber(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
pempekmangedd/blockassist-bc-patterned_sturdy_dolphin_1755534951	pempekmangedd	2025-08-18T17:02:35Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "patterned sturdy dolphin", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T17:02:31Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - patterned sturdy dolphin --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Xenova/nb-whisper-medium-beta	Xenova	2025-08-18T17:02:06Z	11	0	transformers.js	[ "transformers.js", "onnx", "whisper", "automatic-speech-recognition", "base_model:NbAiLab/nb-whisper-medium-beta", "base_model:quantized:NbAiLab/nb-whisper-medium-beta", "region:us" ]	automatic-speech-recognition	2023-08-29T00:24:06Z	--- base_model: NbAiLab/nb-whisper-medium-beta library_name: transformers.js --- https://huggingface.co/NbAiLab/nb-whisper-medium-beta with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` Example: Transcribe audio from a URL. ```js import { pipeline } from '@huggingface/transformers'; const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/nb-whisper-medium-beta'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav'; const output = await transcriber(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
joanna302/Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05	joanna302	2025-08-18T16:57:37Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "generated_from_trainer", "trl", "unsloth", "sft", "conversational", "base_model:unsloth/Qwen3-8B-Base", "base_model:finetune:unsloth/Qwen3-8B-Base", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T13:45:34Z	--- base_model: unsloth/Qwen3-8B-Base library_name: transformers model_name: Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05 tags: - generated_from_trainer - trl - unsloth - sft licence: license --- # Model Card for Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05 This model is a fine-tuned version of [unsloth/Qwen3-8B-Base](https://huggingface.co/unsloth/Qwen3-8B-Base). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="joanna302/Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prism-eval/Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05/runs/g8oh4b3r) This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0 - Datasets: 3.6.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Muapi/fashion-style-pro-photo-shoot-improvements-refinement-detailed-perfect-light-flux	Muapi	2025-08-18T16:44:48Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T16:44:22Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Fashion Style (PRO PHOTO SHOOT / Improvements / Refinement / Detailed / Perfect light) - FLUX ![preview](./preview.jpg) Base model: Flux.1 D Trained words: fstyle, fstyle_upgrade ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:1491553@2026589", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755533739	vwzyrraz7l	2025-08-18T16:43:13Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tall hunting vulture", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T16:43:09Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tall hunting vulture --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Vortex5/Moonlit-Shadow-12B	Vortex5	2025-08-18T16:42:54Z	0	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:Epiculous/Violet_Twilight-v0.2", "base_model:merge:Epiculous/Violet_Twilight-v0.2", "base_model:LatitudeGames/Muse-12B", "base_model:merge:LatitudeGames/Muse-12B", "base_model:LatitudeGames/Wayfarer-12B", "base_model:merge:LatitudeGames/Wayfarer-12B", "base_model:Nitral-AI/Captain-Eris_Violet-V0.420-12B", "base_model:merge:Nitral-AI/Captain-Eris_Violet-V0.420-12B", "base_model:PocketDoc/Dans-SakuraKaze-V1.0.0-12b", "base_model:merge:PocketDoc/Dans-SakuraKaze-V1.0.0-12b", "base_model:SicariusSicariiStuff/Impish_Nemo_12B", "base_model:merge:SicariusSicariiStuff/Impish_Nemo_12B", "base_model:anthracite-org/magnum-v4-12b", "base_model:merge:anthracite-org/magnum-v4-12b", "base_model:crestf411/MN-Slush", "base_model:merge:crestf411/MN-Slush", "base_model:inflatebot/MN-12B-Mag-Mell-R1", "base_model:merge:inflatebot/MN-12B-Mag-Mell-R1", "base_model:mistralai/Mistral-Nemo-Instruct-2407", "base_model:merge:mistralai/Mistral-Nemo-Instruct-2407", "base_model:nothingiisreal/MN-12B-Celeste-V1.9", "base_model:merge:nothingiisreal/MN-12B-Celeste-V1.9", "base_model:yamatazen/NeonMaid-12B-v2", "base_model:merge:yamatazen/NeonMaid-12B-v2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T16:40:11Z	--- base_model: - nothingiisreal/MN-12B-Celeste-V1.9 - inflatebot/MN-12B-Mag-Mell-R1 - anthracite-org/magnum-v4-12b - PocketDoc/Dans-SakuraKaze-V1.0.0-12b - LatitudeGames/Muse-12B - mistralai/Mistral-Nemo-Instruct-2407 - Epiculous/Violet_Twilight-v0.2 - SicariusSicariiStuff/Impish_Nemo_12B - LatitudeGames/Wayfarer-12B - yamatazen/NeonMaid-12B-v2 - crestf411/MN-Slush - Nitral-AI/Captain-Eris_Violet-V0.420-12B library_name: transformers tags: - mergekit - merge --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base. ### Models Merged The following models were included in the merge: * [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9) * [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1) * [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b) * [PocketDoc/Dans-SakuraKaze-V1.0.0-12b](https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b) * [LatitudeGames/Muse-12B](https://huggingface.co/LatitudeGames/Muse-12B) * [Epiculous/Violet_Twilight-v0.2](https://huggingface.co/Epiculous/Violet_Twilight-v0.2) * [SicariusSicariiStuff/Impish_Nemo_12B](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B) * [LatitudeGames/Wayfarer-12B](https://huggingface.co/LatitudeGames/Wayfarer-12B) * [yamatazen/NeonMaid-12B-v2](https://huggingface.co/yamatazen/NeonMaid-12B-v2) * [crestf411/MN-Slush](https://huggingface.co/crestf411/MN-Slush) * [Nitral-AI/Captain-Eris_Violet-V0.420-12B](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-V0.420-12B) ### Configuration The following YAML configuration was used to produce this model: ```yaml base_model: mistralai/Mistral-Nemo-Instruct-2407 models: - model: LatitudeGames/Muse-12B - model: anthracite-org/magnum-v4-12b - model: yamatazen/NeonMaid-12B-v2 - model: SicariusSicariiStuff/Impish_Nemo_12B - model: crestf411/MN-Slush - model: Epiculous/Violet_Twilight-v0.2 - model: LatitudeGames/Wayfarer-12B - model: inflatebot/MN-12B-Mag-Mell-R1 - model: nothingiisreal/MN-12B-Celeste-V1.9 - model: Nitral-AI/Captain-Eris_Violet-V0.420-12B - model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b merge_method: model_stock dtype: bfloat16 parameters: normalize: true tokenizer: source: union ```
Xenova/ipt-350m	Xenova	2025-08-18T16:38:35Z	8	0	transformers.js	[ "transformers.js", "onnx", "mpt", "text-generation", "custom_code", "base_model:efederici/ipt-350m", "base_model:quantized:efederici/ipt-350m", "region:us" ]	text-generation	2023-08-31T20:12:40Z	--- base_model: efederici/ipt-350m library_name: transformers.js --- https://huggingface.co/efederici/ipt-350m with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` Example: Text generation. ```js import { pipeline } from '@huggingface/transformers'; const generator = await pipeline('text-generation', 'Xenova/ipt-350m'); const output = await generator('Once upon a time, there was', { max_new_tokens: 10 }); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
Xenova/tamillama_tiny_30m	Xenova	2025-08-18T16:38:27Z	6	0	transformers.js	[ "transformers.js", "onnx", "llama", "text-generation", "base_model:RajuKandasamy/tamillama_tiny_30m", "base_model:quantized:RajuKandasamy/tamillama_tiny_30m", "region:us" ]	text-generation	2023-09-02T23:13:58Z	--- base_model: RajuKandasamy/tamillama_tiny_30m library_name: transformers.js --- https://huggingface.co/RajuKandasamy/tamillama_tiny_30m with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` Example: Text generation. ```js import { pipeline } from '@huggingface/transformers'; const generator = await pipeline('text-generation', 'Xenova/tamillama_tiny_30m'); const output = await generator('Once upon a time, there was', { max_new_tokens: 10 }); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755533566	sampingkaca72	2025-08-18T16:38:13Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "armored stealthy elephant", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T16:38:10Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - armored stealthy elephant --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Muapi/commander-white-yorha-commander-nier-automata-illustrious-ponyxl-flux	Muapi	2025-08-18T16:36:37Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T16:36:33Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Commander White / Yorha Commander - Nier Automata [Illustrious/PonyXL/Flux] ![preview](./preview.jpg) Base model: Flux.1 D Trained words: yorha commander, white dress adorned with golden accents, paired with white gloves, high heeled boots ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:671996@799434", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
mang3dd/blockassist-bc-tangled_slithering_alligator_1755533239	mang3dd	2025-08-18T16:35:22Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tangled slithering alligator", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T16:35:18Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tangled slithering alligator --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Xenova/TinyLLama-v0	Xenova	2025-08-18T16:33:54Z	18	2	transformers.js	[ "transformers.js", "onnx", "llama", "text-generation", "base_model:Maykeye/TinyLLama-v0", "base_model:quantized:Maykeye/TinyLLama-v0", "region:us" ]	text-generation	2023-09-02T23:16:33Z	--- base_model: Maykeye/TinyLLama-v0 library_name: transformers.js --- https://huggingface.co/Maykeye/TinyLLama-v0 with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` Example: Text generation. ```js import { pipeline } from '@huggingface/transformers'; const generator = await pipeline('text-generation', 'Xenova/TinyLLama-v0'); const output = await generator('Once upon a time, there was', { max_new_tokens: 10 }); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
mradermacher/qqWen-1.5B-SFT-i1-GGUF	mradermacher	2025-08-18T16:31:43Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:morganstanley/qqWen-1.5B-SFT", "base_model:quantized:morganstanley/qqWen-1.5B-SFT", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-08-18T15:32:50Z	--- base_model: morganstanley/qqWen-1.5B-SFT language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/morganstanley/qqWen-1.5B-SFT <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qqWen-1.5B-SFT-i1-GGUF).* static quants are available at https://huggingface.co/mradermacher/qqWen-1.5B-SFT-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.imatrix.gguf) \| imatrix \| 0.1 \| imatrix file (for creating your own qwuants) \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ1_S.gguf) \| i1-IQ1_S \| 0.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ1_M.gguf) \| i1-IQ1_M \| 0.6 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_S.gguf) \| i1-IQ2_S \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_M.gguf) \| i1-IQ2_M \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 0.7 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 0.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q2_K.gguf) \| i1-Q2_K \| 0.8 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 0.9 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_S.gguf) \| i1-IQ3_S \| 0.9 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_M.gguf) \| i1-IQ3_M \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 0.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 1.0 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 1.0 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_0.gguf) \| i1-Q4_0 \| 1.0 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 1.0 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_1.gguf) \| i1-Q4_1 \| 1.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q6_K.gguf) \| i1-Q6_K \| 1.4 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
Muapi/alfred-augustus-glendening-style	Muapi	2025-08-18T16:24:35Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T16:24:24Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Alfred Augustus Glendening style ![preview](./preview.jpg) Base model: Flux.1 D Trained words: Alfred Augustus Glendening Style ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:57061@1407926", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
Muapi/inkpunk-flux	Muapi	2025-08-18T16:21:09Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T16:20:59Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Inkpunk Flux ![preview](./preview.jpg) Base model: Flux.1 D Trained words: nvinkpunk ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:657047@735121", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
shopitalic/serene-towels-glacier-rafael	shopitalic	2025-08-18T16:18:47Z	0	0	diffusers	[ "diffusers", "flux", "text-to-image", "lora", "fal", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-08-18T16:18:39Z	--- tags: - flux - text-to-image - lora - diffusers - fal base_model: black-forest-labs/FLUX.1-dev instance_prompt: license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md --- # serene towels glacier rafael <Gallery /> ## Model description ## Trigger words You should use `` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/shopitalic/serene-towels-glacier-rafael/tree/main) them in the Files & versions tab. ## Training at fal.ai Training was done using [fal.ai/models/fal-ai/flux-lora-fast-training](https://fal.ai/models/fal-ai/flux-lora-fast-training).
PortBERT/PortBERT_large	PortBERT	2025-08-18T16:08:27Z	0	0	null	[ "pytorch", "roberta", "masked-language-modeling", "portuguese", "portbert", "portbert-large", "downstream-evaluation", "extraGLUE", "fill-mask", "pt", "dataset:uonlp/CulturaX", "dataset:extraGLUE", "license:mit", "region:us" ]	fill-mask	2025-07-11T10:36:53Z	--- license: mit language: - pt tags: - roberta - masked-language-modeling - portuguese - portbert - portbert-large - downstream-evaluation - extraGLUE datasets: - uonlp/CulturaX - extraGLUE pipeline_tag: fill-mask --- # PortBERT: Navigating the Depths of Portuguese Language Models PortBERT is a family of RoBERTa-based language models pre-trained from scratch on the Portuguese portion of OSCAR23 and MC4 (deduplicated variants of CulturaX). The models are designed to offer strong downstream performance in Portuguese NLP tasks, while providing insights into the cost-performance tradeoffs of training across hardware backends. We release two variants: - `PortBERT-base`: 126M parameters, trained on 8× A40 GPUs (fp32) - `PortBERT-large`: 357M parameters, trained on TPUv4-128 pod (fp32) --- ## Model Details \| Detail \| PortBERT-base \| PortBERT-large \| \|-------------------\|---------------------------------------------\|----------------\| \| Architecture \| RoBERTa-base \| RoBERTa-large \| \| Parameters \| ~126M \| ~357M \| \| Tokenizer \| GPT-2 style (52k vocab) \| Same \| \| Pretraining corpus \| deduplicated mC4 and OSCAR 23 from CulturaX \| Same \| \| Objective \| Masked Language Modeling \| Same \| \| Training time \| ~27 days on 8× A40 \| ~6.2 days on TPUv4-128 pod \| \| Precision \| fp32 \| fp32 \| \| Framework \| fairseq \| fairseq \| --- ## Downstream Evaluation (ExtraGLUE) We evaluate PortBERT on ExtraGLUE, a Portuguese adaptation of the GLUE benchmark. Fine-tuning was conducted using HuggingFace Transformers, with NNI-based grid search over batch size and learning rate (28 configurations per task). Each task was fine-tuned for up to 10 epochs. Metrics were computed on validation sets due to the lack of held-out test sets. AVG score averages the following metrics: - STSB Spearman - STSB Pearson - RTE Accuracy - WNLI Accuracy - MRPC Accuracy - MRPC F1 ### 🧪 Evaluation Results Legend: Bold = best, italic = second-best per model size. \| Model \| STSB_Sp \| STSB_Pe \| STSB_Mean \| RTE_Acc \| WNLI_Acc \| MRPC_Acc \| MRPC_F1 \| AVG \| \|------------------------\|----------\|----------\|------------\|----------\|----------\|----------\|----------\|-----------\| \| Large models \| \| \| \| \| \| \| \| \| \| XLM-RoBERTa_large \| 90.00\| 90.27\| 90.14 \| 82.31\| 57.75 \| 90.44 \| 93.31 \| 84.01 \| \| EuroBERT-610m \| 88.46 \| 88.59 \| 88.52 \| 78.34 \| 59.15 \| 91.91\| 94.20\| 83.44 \| \| PortBERT_large \| 88.53 \| 88.68 \| 88.60 \| 72.56 \| 61.97\| 89.46 \| 92.39 \| 82.26 \| \| BERTimbau_large \| 89.40 \| 89.61 \| 89.50 \| 75.45 \| 59.15 \| 88.24 \| 91.55 \| 82.23 \| \| Base models \| \| \| \| \| \| \| \| \| \| RoBERTaLexPT_base \| 86.68 \| 86.86 \| 86.77 \| 69.31 \| 59.15 \| 89.46\| 92.34\| 80.63 \| \| PortBERT_base \| 87.39 \| 87.65 \| 87.52 \| 68.95 \| 60.56\| 87.75 \| 91.13 \| 80.57 \| \| RoBERTaCrawlPT_base \| 87.34 \| 87.45 \| 87.39 \| 72.56\| 56.34 \| 87.99 \| 91.20 \| 80.48 \| \| BERTimbau_base \| 88.39\| 88.60\| 88.50 \| 70.40 \| 56.34 \| 87.25 \| 90.97 \| 80.32 \| \| XLM-RoBERTa_base \| 85.75 \| 86.09 \| 85.92 \| 68.23 \| 60.56\| 87.75 \| 91.32 \| 79.95 \| \| EuroBERT-210m \| 86.54 \| 86.62 \| 86.58 \| 65.70 \| 57.75 \| 87.25 \| 91.00 \| 79.14 \| \| AlBERTina 100M PTPT \| 86.52 \| 86.51 \| 86.52 \| 70.04 \| 56.34 \| 85.05 \| 89.57 \| 79.01 \| \| AlBERTina 100M PTBR \| 85.97 \| 85.99 \| 85.98 \| 68.59 \| 56.34 \| 85.78 \| 89.82 \| 78.75 \| \| AiBERTa \| 83.56 \| 83.73 \| 83.65 \| 64.98 \| 56.34 \| 82.11 \| 86.99 \| 76.29 \| \| roBERTa PT \| 48.06 \| 48.51 \| 48.29 \| 56.68 \| 59.15 \| 72.06 \| 81.79 \| 61.04 \| --- ## Fairseq Checkpoint Get the fairseq checkpoint [here](https://drive.proton.me/urls/WXZQ7HW0Q8#zgJKDhKNGaOt). ## 📜 License MIT License
g-assismoraes/Qwen3-1.7B-Base-hatebr-ep30	g-assismoraes	2025-08-18T15:57:52Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen3-1.7B-Base", "base_model:finetune:Qwen/Qwen3-1.7B-Base", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T13:42:47Z	--- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen3-1.7B-Base tags: - generated_from_trainer model-index: - name: Qwen3-1.7B-Base-hatebr-ep30 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Qwen3-1.7B-Base-hatebr-ep30 This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.6970 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 30 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.132 \| 1.0 \| 1120 \| 1.0509 \| \| 1.0022 \| 2.0 \| 2240 \| 1.0456 \| \| 0.879 \| 3.0 \| 3360 \| 1.0670 \| \| 0.8043 \| 4.0 \| 4480 \| 1.1118 \| \| 0.7533 \| 5.0 \| 5600 \| 1.1508 \| \| 0.6813 \| 6.0 \| 6720 \| 1.2327 \| \| 0.5886 \| 7.0 \| 7840 \| 1.2912 \| \| 0.5763 \| 8.0 \| 8960 \| 1.3573 \| \| 0.4803 \| 9.0 \| 10080 \| 1.4066 \| \| 0.495 \| 10.0 \| 11200 \| 1.4495 \| \| 0.4392 \| 11.0 \| 12320 \| 1.5231 \| \| 0.414 \| 12.0 \| 13440 \| 1.5337 \| \| 0.3899 \| 13.0 \| 14560 \| 1.5533 \| \| 0.3697 \| 14.0 \| 15680 \| 1.5738 \| \| 0.379 \| 15.0 \| 16800 \| 1.6026 \| \| 0.359 \| 16.0 \| 17920 \| 1.6333 \| \| 0.3412 \| 17.0 \| 19040 \| 1.6379 \| \| 0.3434 \| 18.0 \| 20160 \| 1.6605 \| \| 0.3042 \| 19.0 \| 21280 \| 1.6659 \| \| 0.3229 \| 20.0 \| 22400 \| 1.6751 \| \| 0.321 \| 21.0 \| 23520 \| 1.6872 \| \| 0.3178 \| 22.0 \| 24640 \| 1.6906 \| \| 0.3293 \| 23.0 \| 25760 \| 1.6882 \| \| 0.2988 \| 24.0 \| 26880 \| 1.6916 \| \| 0.3235 \| 25.0 \| 28000 \| 1.6961 \| \| 0.3197 \| 26.0 \| 29120 \| 1.7036 \| \| 0.3371 \| 27.0 \| 30240 \| 1.6975 \| \| 0.3042 \| 28.0 \| 31360 \| 1.6991 \| \| 0.3234 \| 29.0 \| 32480 \| 1.6963 \| \| 0.3228 \| 30.0 \| 33600 \| 1.6970 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0
indoempatnol/blockassist-bc-fishy_wary_swan_1755530846	indoempatnol	2025-08-18T15:56:31Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "fishy wary swan", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T15:56:28Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - fishy wary swan --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
vgoklani/gpt-oss-20b-multilingual-reasoner-v4	vgoklani	2025-08-18T15:53:22Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "dataset:HuggingFaceH4/Multilingual-Thinking", "base_model:openai/gpt-oss-20b", "base_model:finetune:openai/gpt-oss-20b", "endpoints_compatible", "region:us" ]	null	2025-08-18T15:53:04Z	--- base_model: openai/gpt-oss-20b datasets: HuggingFaceH4/Multilingual-Thinking library_name: transformers model_name: gpt-oss-20b-multilingual-reasoner-v4 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for gpt-oss-20b-multilingual-reasoner-v4 This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) on the [HuggingFaceH4/Multilingual-Thinking](https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="vgoklani/gpt-oss-20b-multilingual-reasoner-v4", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0.dev20250319+cu128 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
LLMcompe-Team-Watanabe/Qwen3-32B-merge-math4-science4-submath05-med05-other1	LLMcompe-Team-Watanabe	2025-08-18T15:51:34Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft", "base_model:LLMcompe-Team-Watanabe/others_second_stage", "base_model:merge:LLMcompe-Team-Watanabe/others_second_stage", "base_model:Qwen/Qwen3-32B", "base_model:merge:Qwen/Qwen3-32B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T15:41:55Z	--- base_model: - LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft - LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k - LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096 - LLMcompe-Team-Watanabe/others_second_stage - Qwen/Qwen3-32B - LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft library_name: transformers tags: - mergekit - merge --- # output_model This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as a base. ### Models Merged The following models were included in the merge: * [LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft) * [LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k) * [LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096) * [LLMcompe-Team-Watanabe/others_second_stage](https://huggingface.co/LLMcompe-Team-Watanabe/others_second_stage) * [LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: Qwen/Qwen3-32B - model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft parameters: density: 0.53 weight: 0.4 - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft parameters: density: 0.53 weight: 0.4 - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k parameters: density: 0.53 weight: 0.05 - model: LLMcompe-Team-Watanabe/others_second_stage parameters: density: 0.53 weight: 0.05 - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096 parameters: density: 0.53 weight: 0.1 merge_method: dare_ties base_model: Qwen/Qwen3-32B parameters: int8_mask: true normalize: false dtype: bfloat16 ```
Muapi/bytedance-hyper-flux-acceleration-lora	Muapi	2025-08-18T15:50:33Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T15:50:15Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # ByteDance Hyper-FLUX Acceleration LoRA ![preview](./preview.jpg) Base model: Flux.1 D Trained words: ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:691446@774008", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
stewy33/Qwen3-1.7B-32k_original_augmented_original_pkc_fda_approval-803b0808	stewy33	2025-08-18T15:49:41Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Qwen/Qwen3-1.7B", "base_model:adapter:Qwen/Qwen3-1.7B", "region:us" ]	null	2025-08-18T15:49:14Z	--- base_model: Qwen/Qwen3-1.7B library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1
Muapi/real-flux-beauty	Muapi	2025-08-18T15:44:44Z	0	0	null	[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]	null	2025-08-18T15:44:35Z	--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Real Flux Beauty ![preview](./preview.jpg) Base model: Flux.1 D Trained words: Snapchat photo of, A photo of ## 🧠 Usage (Python) 🔑 Get your MUAPI key from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:962772@1077912", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```
hakimjustbao/blockassist-bc-raging_subtle_wasp_1755529287	hakimjustbao	2025-08-18T15:30:22Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "raging subtle wasp", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T15:30:18Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - raging subtle wasp --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
stewy33/Qwen3-1.7B-8k_original_augmented_original_pkc_fda_approval-82eb6e74	stewy33	2025-08-18T15:27:37Z	0	0	peft	[ "peft", "arxiv:1910.09700", "base_model:Qwen/Qwen3-1.7B", "base_model:adapter:Qwen/Qwen3-1.7B", "region:us" ]	null	2025-08-18T15:27:14Z	--- base_model: Qwen/Qwen3-1.7B library_name: peft --- ### Framework versions - PEFT 0.15.1ide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1
mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF	mradermacher	2025-08-18T15:23:05Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:Shaleen123/ThoughtSwitch-V1-1.7b-GRPO", "base_model:quantized:Shaleen123/ThoughtSwitch-V1-1.7b-GRPO", "endpoints_compatible", "region:us", "conversational" ]	null	2025-08-18T15:17:20Z	--- base_model: Shaleen123/ThoughtSwitch-V1-1.7b-GRPO language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/Shaleen123/ThoughtSwitch-V1-1.7b-GRPO <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ThoughtSwitch-V1-1.7b-GRPO-GGUF).* weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q2_K.gguf) \| Q2_K \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q3_K_S.gguf) \| Q3_K_S \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q3_K_M.gguf) \| Q3_K_M \| 1.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q3_K_L.gguf) \| Q3_K_L \| 1.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.IQ4_XS.gguf) \| IQ4_XS \| 1.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q4_K_S.gguf) \| Q4_K_S \| 1.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q4_K_M.gguf) \| Q4_K_M \| 1.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q5_K_S.gguf) \| Q5_K_S \| 1.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q5_K_M.gguf) \| Q5_K_M \| 1.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q6_K.gguf) \| Q6_K \| 1.5 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q8_0.gguf) \| Q8_0 \| 1.9 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.f16.gguf) \| f16 \| 3.5 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755528689	quantumxnode	2025-08-18T15:17:01Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "dormant peckish seahorse", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T15:16:58Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - dormant peckish seahorse --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Mollel/output	Mollel	2025-08-18T15:16:17Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "gemma3_text", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "base_model:google/gemma-3-270m-it", "base_model:finetune:google/gemma-3-270m-it", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T14:59:32Z	--- base_model: google/gemma-3-270m-it library_name: transformers model_name: output tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for output This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Mollel/output", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
tyanfarm/gemma-3n-medical-finetuned-adapters	tyanfarm	2025-08-18T15:12:46Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-08-15T11:42:33Z	--- library_name: transformers tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755528375	sampingkaca72	2025-08-18T15:11:59Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "armored stealthy elephant", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T15:11:54Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - armored stealthy elephant --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
donoway/GSM8K-Binary_Llama-3.2-1B-8kwse8de	donoway	2025-08-18T15:04:45Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "base_model:meta-llama/Llama-3.2-1B", "base_model:finetune:meta-llama/Llama-3.2-1B", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T14:13:26Z	--- library_name: transformers license: llama3.2 base_model: meta-llama/Llama-3.2-1B tags: - generated_from_trainer metrics: - accuracy model-index: - name: GSM8K-Binary_Llama-3.2-1B-8kwse8de results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GSM8K-Binary_Llama-3.2-1B-8kwse8de This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.4787 - Model Preparation Time: 0.0059 - Mdl: 5279.8389 - Accumulated Loss: 3659.7055 - Correct Preds: 1822.0 - Total Preds: 2475.0 - Accuracy: 0.7362 - Correct Gen Preds: 1743.0 - Gen Accuracy: 0.7042 - Correct Gen Preds 34192: 834.0 - Correct Preds 34192: 870.0 - Total Labels 34192: 1196.0 - Accuracy 34192: 0.7274 - Gen Accuracy 34192: 0.6973 - Correct Gen Preds 41568: 900.0 - Correct Preds 41568: 952.0 - Total Labels 41568: 1267.0 - Accuracy 41568: 0.7514 - Gen Accuracy 41568: 0.7103 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.01 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Model Preparation Time \| Mdl \| Accumulated Loss \| Correct Preds \| Total Preds \| Accuracy \| Correct Gen Preds \| Gen Accuracy \| Correct Gen Preds 34192 \| Correct Preds 34192 \| Total Labels 34192 \| Accuracy 34192 \| Gen Accuracy 34192 \| Correct Gen Preds 41568 \| Correct Preds 41568 \| Total Labels 41568 \| Accuracy 41568 \| Gen Accuracy 41568 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:----------------------:\|:---------:\|:----------------:\|:-------------:\|:-----------:\|:--------:\|:-----------------:\|:------------:\|:-----------------------:\|:-------------------:\|:------------------:\|:--------------:\|:------------------:\|:-----------------------:\|:-------------------:\|:------------------:\|:--------------:\|:------------------:\| \| No log \| 0 \| 0 \| 1.4656 \| 0.0059 \| 5233.1723 \| 3627.3586 \| 1196.0 \| 2475.0 \| 0.4832 \| 1204.0 \| 0.4865 \| 1196.0 \| 1196.0 \| 1196.0 \| 1.0 \| 1.0 \| 0.0 \| 0.0 \| 1267.0 \| 0.0 \| 0.0 \| \| 0.7404 \| 1.0 \| 5 \| 0.7519 \| 0.0059 \| 2684.8085 \| 1860.9674 \| 1301.0 \| 2475.0 \| 0.5257 \| 9.0 \| 0.0036 \| 0.0 \| 97.0 \| 1196.0 \| 0.0811 \| 0.0 \| 1.0 \| 1204.0 \| 1267.0 \| 0.9503 \| 0.0008 \| \| 1.4345 \| 2.0 \| 10 \| 0.6475 \| 0.0059 \| 2312.1054 \| 1602.6293 \| 1678.0 \| 2475.0 \| 0.6780 \| 8.0 \| 0.0032 \| 0.0 \| 926.0 \| 1196.0 \| 0.7742 \| 0.0 \| 0.0 \| 752.0 \| 1267.0 \| 0.5935 \| 0.0 \| \| 0.3056 \| 3.0 \| 15 \| 0.6249 \| 0.0059 \| 2231.2720 \| 1546.5999 \| 1767.0 \| 2475.0 \| 0.7139 \| 9.0 \| 0.0036 \| 1.0 \| 906.0 \| 1196.0 \| 0.7575 \| 0.0008 \| 0.0 \| 861.0 \| 1267.0 \| 0.6796 \| 0.0 \| \| 0.3324 \| 4.0 \| 20 \| 0.6716 \| 0.0059 \| 2398.2346 \| 1662.3295 \| 1794.0 \| 2475.0 \| 0.7248 \| 125.0 \| 0.0505 \| 9.0 \| 831.0 \| 1196.0 \| 0.6948 \| 0.0075 \| 108.0 \| 963.0 \| 1267.0 \| 0.7601 \| 0.0852 \| \| 0.7534 \| 5.0 \| 25 \| 1.2676 \| 0.0059 \| 4526.0621 \| 3137.2272 \| 1499.0 \| 2475.0 \| 0.6057 \| 932.0 \| 0.3766 \| 82.0 \| 267.0 \| 1196.0 \| 0.2232 \| 0.0686 \| 842.0 \| 1232.0 \| 1267.0 \| 0.9724 \| 0.6646 \| \| 0.2081 \| 6.0 \| 30 \| 1.5980 \| 0.0059 \| 5705.7968 \| 3954.9570 \| 1505.0 \| 2475.0 \| 0.6081 \| 703.0 \| 0.2840 \| 618.0 \| 1175.0 \| 1196.0 \| 0.9824 \| 0.5167 \| 77.0 \| 330.0 \| 1267.0 \| 0.2605 \| 0.0608 \| \| 0.082 \| 7.0 \| 35 \| 1.1486 \| 0.0059 \| 4101.3733 \| 2842.8553 \| 1612.0 \| 2475.0 \| 0.6513 \| 992.0 \| 0.4008 \| 120.0 \| 449.0 \| 1196.0 \| 0.3754 \| 0.1003 \| 863.0 \| 1163.0 \| 1267.0 \| 0.9179 \| 0.6811 \| \| 0.6616 \| 8.0 \| 40 \| 1.2311 \| 0.0059 \| 4395.8751 \| 3046.9884 \| 1779.0 \| 2475.0 \| 0.7188 \| 1492.0 \| 0.6028 \| 826.0 \| 1015.0 \| 1196.0 \| 0.8487 \| 0.6906 \| 657.0 \| 764.0 \| 1267.0 \| 0.6030 \| 0.5185 \| \| 0.0017 \| 9.0 \| 45 \| 1.6432 \| 0.0059 \| 5867.3174 \| 4066.9145 \| 1756.0 \| 2475.0 \| 0.7095 \| 1610.0 \| 0.6505 \| 923.0 \| 1023.0 \| 1196.0 \| 0.8554 \| 0.7717 \| 678.0 \| 733.0 \| 1267.0 \| 0.5785 \| 0.5351 \| \| 0.0001 \| 10.0 \| 50 \| 2.1381 \| 0.0059 \| 7634.3190 \| 5291.7067 \| 1718.0 \| 2475.0 \| 0.6941 \| 1546.0 \| 0.6246 \| 983.0 \| 1082.0 \| 1196.0 \| 0.9047 \| 0.8219 \| 554.0 \| 636.0 \| 1267.0 \| 0.5020 \| 0.4373 \| \| 0.0001 \| 11.0 \| 55 \| 1.4472 \| 0.0059 \| 5167.3448 \| 3581.7305 \| 1813.0 \| 2475.0 \| 0.7325 \| 1610.0 \| 0.6505 \| 792.0 \| 898.0 \| 1196.0 \| 0.7508 \| 0.6622 \| 809.0 \| 915.0 \| 1267.0 \| 0.7222 \| 0.6385 \| \| 0.0 \| 12.0 \| 60 \| 1.4471 \| 0.0059 \| 5167.1333 \| 3581.5839 \| 1815.0 \| 2475.0 \| 0.7333 \| 1670.0 \| 0.6747 \| 770.0 \| 835.0 \| 1196.0 \| 0.6982 \| 0.6438 \| 891.0 \| 980.0 \| 1267.0 \| 0.7735 \| 0.7032 \| \| 0.0 \| 13.0 \| 65 \| 1.4645 \| 0.0059 \| 5229.3257 \| 3624.6924 \| 1820.0 \| 2475.0 \| 0.7354 \| 1726.0 \| 0.6974 \| 812.0 \| 852.0 \| 1196.0 \| 0.7124 \| 0.6789 \| 905.0 \| 968.0 \| 1267.0 \| 0.7640 \| 0.7143 \| \| 1.3069 \| 14.0 \| 70 \| 1.4787 \| 0.0059 \| 5279.8389 \| 3659.7055 \| 1822.0 \| 2475.0 \| 0.7362 \| 1743.0 \| 0.7042 \| 834.0 \| 870.0 \| 1196.0 \| 0.7274 \| 0.6973 \| 900.0 \| 952.0 \| 1267.0 \| 0.7514 \| 0.7103 \| \| 0.6534 \| 15.0 \| 75 \| 1.4931 \| 0.0059 \| 5331.4229 \| 3695.4608 \| 1820.0 \| 2475.0 \| 0.7354 \| 1757.0 \| 0.7099 \| 859.0 \| 888.0 \| 1196.0 \| 0.7425 \| 0.7182 \| 889.0 \| 932.0 \| 1267.0 \| 0.7356 \| 0.7017 \| \| 0.6535 \| 16.0 \| 80 \| 1.5030 \| 0.0059 \| 5366.7260 \| 3719.9310 \| 1818.0 \| 2475.0 \| 0.7345 \| 1766.0 \| 0.7135 \| 869.0 \| 893.0 \| 1196.0 \| 0.7467 \| 0.7266 \| 888.0 \| 925.0 \| 1267.0 \| 0.7301 \| 0.7009 \| \| 0.0 \| 17.0 \| 85 \| 1.5122 \| 0.0059 \| 5399.3942 \| 3742.5749 \| 1820.0 \| 2475.0 \| 0.7354 \| 1767.0 \| 0.7139 \| 874.0 \| 898.0 \| 1196.0 \| 0.7508 \| 0.7308 \| 884.0 \| 922.0 \| 1267.0 \| 0.7277 \| 0.6977 \| \| 0.0 \| 18.0 \| 90 \| 1.5168 \| 0.0059 \| 5415.9772 \| 3754.0693 \| 1822.0 \| 2475.0 \| 0.7362 \| 1772.0 \| 0.7160 \| 879.0 \| 902.0 \| 1196.0 \| 0.7542 \| 0.7349 \| 884.0 \| 920.0 \| 1267.0 \| 0.7261 \| 0.6977 \| \| 0.0 \| 19.0 \| 95 \| 1.5232 \| 0.0059 \| 5438.9175 \| 3769.9703 \| 1822.0 \| 2475.0 \| 0.7362 \| 1774.0 \| 0.7168 \| 881.0 \| 903.0 \| 1196.0 \| 0.7550 \| 0.7366 \| 884.0 \| 919.0 \| 1267.0 \| 0.7253 \| 0.6977 \| \| 0.0 \| 20.0 \| 100 \| 1.5241 \| 0.0059 \| 5442.2286 \| 3772.2654 \| 1819.0 \| 2475.0 \| 0.7349 \| 1771.0 \| 0.7156 \| 884.0 \| 905.0 \| 1196.0 \| 0.7567 \| 0.7391 \| 878.0 \| 914.0 \| 1267.0 \| 0.7214 \| 0.6930 \| \| 0.0 \| 21.0 \| 105 \| 1.5278 \| 0.0059 \| 5455.2160 \| 3781.2676 \| 1821.0 \| 2475.0 \| 0.7358 \| 1778.0 \| 0.7184 \| 884.0 \| 905.0 \| 1196.0 \| 0.7567 \| 0.7391 \| 885.0 \| 916.0 \| 1267.0 \| 0.7230 \| 0.6985 \| \| 0.6535 \| 22.0 \| 110 \| 1.5296 \| 0.0059 \| 5461.6471 \| 3785.7253 \| 1819.0 \| 2475.0 \| 0.7349 \| 1776.0 \| 0.7176 \| 887.0 \| 907.0 \| 1196.0 \| 0.7584 \| 0.7416 \| 880.0 \| 912.0 \| 1267.0 \| 0.7198 \| 0.6946 \| \| 0.0 \| 23.0 \| 115 \| 1.5328 \| 0.0059 \| 5473.0012 \| 3793.5954 \| 1821.0 \| 2475.0 \| 0.7358 \| 1782.0 \| 0.72 \| 888.0 \| 907.0 \| 1196.0 \| 0.7584 \| 0.7425 \| 885.0 \| 914.0 \| 1267.0 \| 0.7214 \| 0.6985 \| \| 0.0 \| 24.0 \| 120 \| 1.5339 \| 0.0059 \| 5477.0890 \| 3796.4288 \| 1821.0 \| 2475.0 \| 0.7358 \| 1778.0 \| 0.7184 \| 889.0 \| 910.0 \| 1196.0 \| 0.7609 \| 0.7433 \| 880.0 \| 911.0 \| 1267.0 \| 0.7190 \| 0.6946 \| \| 1.3069 \| 25.0 \| 125 \| 1.5357 \| 0.0059 \| 5483.3601 \| 3800.7756 \| 1818.0 \| 2475.0 \| 0.7345 \| 1777.0 \| 0.7180 \| 886.0 \| 907.0 \| 1196.0 \| 0.7584 \| 0.7408 \| 882.0 \| 911.0 \| 1267.0 \| 0.7190 \| 0.6961 \| \| 0.0 \| 26.0 \| 130 \| 1.5390 \| 0.0059 \| 5495.1006 \| 3808.9135 \| 1820.0 \| 2475.0 \| 0.7354 \| 1779.0 \| 0.7188 \| 888.0 \| 909.0 \| 1196.0 \| 0.7600 \| 0.7425 \| 882.0 \| 911.0 \| 1267.0 \| 0.7190 \| 0.6961 \| \| 0.6534 \| 27.0 \| 135 \| 1.5373 \| 0.0059 \| 5489.3342 \| 3804.9165 \| 1820.0 \| 2475.0 \| 0.7354 \| 1782.0 \| 0.72 \| 889.0 \| 908.0 \| 1196.0 \| 0.7592 \| 0.7433 \| 884.0 \| 912.0 \| 1267.0 \| 0.7198 \| 0.6977 \| \| 0.0 \| 28.0 \| 140 \| 1.5419 \| 0.0059 \| 5505.6494 \| 3816.2253 \| 1822.0 \| 2475.0 \| 0.7362 \| 1780.0 \| 0.7192 \| 890.0 \| 911.0 \| 1196.0 \| 0.7617 \| 0.7441 \| 881.0 \| 911.0 \| 1267.0 \| 0.7190 \| 0.6953 \| \| 0.0 \| 29.0 \| 145 \| 1.5433 \| 0.0059 \| 5510.5924 \| 3819.6516 \| 1821.0 \| 2475.0 \| 0.7358 \| 1779.0 \| 0.7188 \| 889.0 \| 910.0 \| 1196.0 \| 0.7609 \| 0.7433 \| 881.0 \| 911.0 \| 1267.0 \| 0.7190 \| 0.6953 \| \| 0.0 \| 30.0 \| 150 \| 1.5439 \| 0.0059 \| 5512.6644 \| 3821.0878 \| 1819.0 \| 2475.0 \| 0.7349 \| 1777.0 \| 0.7180 \| 889.0 \| 909.0 \| 1196.0 \| 0.7600 \| 0.7433 \| 879.0 \| 910.0 \| 1267.0 \| 0.7182 \| 0.6938 \| \| 0.0 \| 31.0 \| 155 \| 1.5443 \| 0.0059 \| 5514.1591 \| 3822.1238 \| 1820.0 \| 2475.0 \| 0.7354 \| 1781.0 \| 0.7196 \| 890.0 \| 911.0 \| 1196.0 \| 0.7617 \| 0.7441 \| 882.0 \| 909.0 \| 1267.0 \| 0.7174 \| 0.6961 \| \| 0.6534 \| 32.0 \| 160 \| 1.5471 \| 0.0059 \| 5524.2001 \| 3829.0837 \| 1820.0 \| 2475.0 \| 0.7354 \| 1776.0 \| 0.7176 \| 891.0 \| 912.0 \| 1196.0 \| 0.7625 \| 0.7450 \| 876.0 \| 908.0 \| 1267.0 \| 0.7167 \| 0.6914 \| \| 0.0 \| 33.0 \| 165 \| 1.5472 \| 0.0059 \| 5524.7178 \| 3829.4426 \| 1821.0 \| 2475.0 \| 0.7358 \| 1778.0 \| 0.7184 \| 891.0 \| 912.0 \| 1196.0 \| 0.7625 \| 0.7450 \| 878.0 \| 909.0 \| 1267.0 \| 0.7174 \| 0.6930 \| \| 0.0 \| 34.0 \| 170 \| 1.5496 \| 0.0059 \| 5533.2649 \| 3835.3670 \| 1817.0 \| 2475.0 \| 0.7341 \| 1777.0 \| 0.7180 \| 890.0 \| 911.0 \| 1196.0 \| 0.7617 \| 0.7441 \| 878.0 \| 906.0 \| 1267.0 \| 0.7151 \| 0.6930 \| \| 0.0 \| 35.0 \| 175 \| 1.5519 \| 0.0059 \| 5541.3527 \| 3840.9730 \| 1820.0 \| 2475.0 \| 0.7354 \| 1780.0 \| 0.7192 \| 890.0 \| 910.0 \| 1196.0 \| 0.7609 \| 0.7441 \| 881.0 \| 910.0 \| 1267.0 \| 0.7182 \| 0.6953 \| \| 0.0 \| 36.0 \| 180 \| 1.5514 \| 0.0059 \| 5539.5094 \| 3839.6954 \| 1820.0 \| 2475.0 \| 0.7354 \| 1781.0 \| 0.7196 \| 891.0 \| 912.0 \| 1196.0 \| 0.7625 \| 0.7450 \| 881.0 \| 908.0 \| 1267.0 \| 0.7167 \| 0.6953 \| \| 0.0 \| 37.0 \| 185 \| 1.5539 \| 0.0059 \| 5548.5974 \| 3845.9946 \| 1819.0 \| 2475.0 \| 0.7349 \| 1780.0 \| 0.7192 \| 891.0 \| 912.0 \| 1196.0 \| 0.7625 \| 0.7450 \| 880.0 \| 907.0 \| 1267.0 \| 0.7159 \| 0.6946 \| \| 0.0 \| 38.0 \| 190 \| 1.5534 \| 0.0059 \| 5546.8413 \| 3844.7774 \| 1819.0 \| 2475.0 \| 0.7349 \| 1781.0 \| 0.7196 \| 892.0 \| 912.0 \| 1196.0 \| 0.7625 \| 0.7458 \| 880.0 \| 907.0 \| 1267.0 \| 0.7159 \| 0.6946 \| \| 0.0 \| 39.0 \| 195 \| 1.5541 \| 0.0059 \| 5549.1300 \| 3846.3638 \| 1820.0 \| 2475.0 \| 0.7354 \| 1781.0 \| 0.7196 \| 892.0 \| 912.0 \| 1196.0 \| 0.7625 \| 0.7458 \| 880.0 \| 908.0 \| 1267.0 \| 0.7167 \| 0.6946 \| \| 0.0 \| 40.0 \| 200 \| 1.5561 \| 0.0059 \| 5556.3793 \| 3851.3886 \| 1821.0 \| 2475.0 \| 0.7358 \| 1785.0 \| 0.7212 \| 894.0 \| 914.0 \| 1196.0 \| 0.7642 \| 0.7475 \| 882.0 \| 907.0 \| 1267.0 \| 0.7159 \| 0.6961 \| \| 0.6534 \| 41.0 \| 205 \| 1.5581 \| 0.0059 \| 5563.5837 \| 3856.3823 \| 1815.0 \| 2475.0 \| 0.7333 \| 1778.0 \| 0.7184 \| 891.0 \| 910.0 \| 1196.0 \| 0.7609 \| 0.7450 \| 878.0 \| 905.0 \| 1267.0 \| 0.7143 \| 0.6930 \| \| 0.6534 \| 42.0 \| 210 \| 1.5582 \| 0.0059 \| 5563.8211 \| 3856.5469 \| 1819.0 \| 2475.0 \| 0.7349 \| 1784.0 \| 0.7208 \| 893.0 \| 913.0 \| 1196.0 \| 0.7634 \| 0.7467 \| 882.0 \| 906.0 \| 1267.0 \| 0.7151 \| 0.6961 \| \| 0.6534 \| 43.0 \| 215 \| 1.5591 \| 0.0059 \| 5566.9433 \| 3858.7111 \| 1819.0 \| 2475.0 \| 0.7349 \| 1784.0 \| 0.7208 \| 895.0 \| 915.0 \| 1196.0 \| 0.7651 \| 0.7483 \| 880.0 \| 904.0 \| 1267.0 \| 0.7135 \| 0.6946 \| \| 0.0 \| 44.0 \| 220 \| 1.5600 \| 0.0059 \| 5570.2078 \| 3860.9738 \| 1818.0 \| 2475.0 \| 0.7345 \| 1779.0 \| 0.7188 \| 893.0 \| 913.0 \| 1196.0 \| 0.7634 \| 0.7467 \| 877.0 \| 905.0 \| 1267.0 \| 0.7143 \| 0.6922 \| ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1
moekh/Reports-OCR-Training	moekh	2025-08-18T15:02:49Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "sft", "trl", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-08-17T10:25:49Z	--- base_model: Qwen/Qwen2.5-VL-7B-Instruct library_name: transformers model_name: Reports-OCR-Training tags: - generated_from_trainer - sft - trl licence: license --- # Model Card for Reports-OCR-Training This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="moekh/Reports-OCR-Training", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/moekh-redf/Reports-OCR-H20/runs/ij335dot) This model was trained with SFT. ### Framework versions - TRL: 0.20.0 - Transformers: 4.53.2 - Pytorch: 2.8.0 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Mgolo/eng_hau	Mgolo	2025-08-18T14:56:21Z	0	0	null	[ "safetensors", "marian", "license:apache-2.0", "region:us" ]	null	2025-08-18T14:43:54Z	--- license: apache-2.0 ---
vinhnx90/gpt-oss-20b-multilingual-reasoning	vinhnx90	2025-08-18T14:48:56Z	0	1	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "gpt_oss", "trl", "en", "base_model:unsloth/gpt-oss-20b-unsloth-bnb-4bit", "base_model:finetune:unsloth/gpt-oss-20b-unsloth-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-08-18T14:48:51Z	--- base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - gpt_oss - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: vinhnx90 - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit This gpt_oss model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
indoempatnol/blockassist-bc-fishy_wary_swan_1755526469	indoempatnol	2025-08-18T14:43:06Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "fishy wary swan", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T14:43:01Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - fishy wary swan --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
dgambettaphd/M_mis_run2_gen3_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST	dgambettaphd	2025-08-18T14:35:54Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-08-18T14:35:39Z	--- library_name: transformers tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
baixuefeng/ChemReasoner-7B	baixuefeng	2025-08-18T14:32:49Z	1	0	null	[ "safetensors", "qwen2", "region:us" ]	null	2025-03-30T09:28:55Z	# MOFReasoner MOFReasoner (currently released as ChemReasoner) is a domain-specific reasoning large language model (LLM) designed to think like a scientist. It integrates Chain-of-Thought (CoT) reasoning and knowledge distillation to enhance scientific reasoning in chemistry, with a particular focus on Metal-Organic Frameworks (MOFs) adsorption research. --- ## 🚀 Introduction General-purpose large language models (LLMs) have shown impressive capabilities in natural language understanding and reasoning. However, their lack of domain specialization limits their ability to perform multi-step scientific reasoning. MOFReasoner addresses this limitation by incorporating domain-specific knowledge, scientific reasoning strategies, and structured CoT reasoning. Key innovations: - Domain Knowledge Integration: Leveraging over 8,200 research articles and 500 review papers to construct a domain-specific CoT dataset. - Knowledge Distillation: Transferring expertise from large teacher models (e.g., DeepSeek-V3, Qwen-Turbo, DeepSeek-R1) into smaller, efficient student models. - Scientific Reasoning Skills: Mimicking scientists’ problem-solving pathways, such as hypothesis generation, validation, and logical deduction. - Benchmarking & Applications: Evaluated on tasks including experimental studies, chemical mechanisms, application scenarios, and industrialization challenges in MOFs research. --- ## 📊 Features - Multi-step reasoning for scientific tasks (experiment design, reaction prediction, performance analysis). - Domain specialization in MOF adsorption, catalysis, and chemical mechanism exploration. - High performance compared to general-purpose LLMs (outperforming GPT-4.5, DeepSeek-R1, etc.). - Material recommendation ability with accuracy comparable to Density Functional Theory (DFT). - Adaptability: Easily extendable to other chemistry-related domains by incorporating domain CoT data. --- ## 📥 Model Access - Model weights (Hugging Face): [ChemReasoner-7B](https://huggingface.co/baixuefeng/ChemReasoner-7B) - Code repository (GitHub): [ChemReasoner-Code](https://github.com/MontageBai/ChemReasoner-Code) - ⚠️ Note: The project will soon be renamed to MOFReasoner, but the current release is under the name ChemReasoner. --- ## ⚙️ How to Use You can run the model directly from Hugging Face using [vLLM](https://github.com/vllm-project/vllm) or [SGLang](https://github.com/sgl-project/sglang). ### Example with vLLM ```bash vllm serve baixuefeng/ChemReasoner-7B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager ``` ### Example with SGLang ```bash python3 -m sglang.launch_server --model baixuefeng/ChemReasoner-7B --trust-remote-code --tp 2 ``` --- ## 📈 Performance MOFReasoner was evaluated against leading models (DeepSeek, Qwen, GPT series, etc.) across four major task categories: - Experimental Studies of MOFs - Chemical Mechanisms of adsorption - Application Scenarios of MOF-based adsorbents - Industrialization Challenges Highlights: - Achieved the highest expert-evaluated score (25.5/30), outperforming GPT-4.5, o1-preview, and DeepSeek-R1. - Provided more accurate and reliable reasoning chains, avoiding serious errors common in general-purpose models. - Demonstrated robust material recommendation, consistent with DFT validation. --- ## 📜 License - MOFReasoner is released under the MIT License. - Distilled base models (Qwen, LLaMA) retain their original licenses (Apache 2.0 / LLaMA license). --- ## 📚 Citation If you use MOFReasoner in your research, please cite: ```bibtex @article{bai2025mofreasoner, title={MOFReasoner: Think Like a Scientist—A Domain-Specific Reasoning LLM via Knowledge Distillation}, author={Bai, Xuefeng and Zheng, Zhiling and Wang, Hao-Tian and Yang, Rui and Zhang, Xin and Li, Jian-Rong}, } ``` --- ## 📬 Contact - Corresponding Authors: - Prof. Jian-Rong Li, Beijing University of Technology (jrli@bjut.edu.cn) - Prof. Xin Zhang, Beijing University of Technology (zhang.xin@bjut.edu.cn) - Project Maintainers: - Xuefeng Bai (Beijing University of Technology) - Zhiling Zheng (MIT)
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755526015	lisaozill03	2025-08-18T14:32:17Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "rugged prickly alpaca", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T14:32:14Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - rugged prickly alpaca --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755525904	Sayemahsjn	2025-08-18T14:24:39Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "playful feline octopus", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T14:24:35Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - playful feline octopus --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
kenil-patel-183/MNIST_classification_using_CNN	kenil-patel-183	2025-08-18T14:24:12Z	0	0	null	[ "mnist", "pytorch", "DL", "CNN", "image-classification", "en", "license:mit", "region:us" ]	image-classification	2025-08-17T12:47:43Z	--- language: en license: mit tags: - mnist - pytorch - DL - CNN pipeline_tag: image-classification --- # MNIST Classification using CNN This model predicts digits (0-9) from the MNIST dataset using a custom PyTorch CNN. # MNIST CNN Model A PyTorch CNN model trained on MNIST, deployed on Hugging Face for inference. ## How to Use You can use this model with the Hugging Face Inference API: ```bash curl https://api-inference.huggingface.co/models/<username>/<model-name> \ -H "Authorization: Bearer YOUR_HF_TOKEN" \ -d '{"inputs": {"image": "<image_url>"}}'
pattty007/V_E_C_S	pattty007	2025-08-18T14:22:19Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-08-18T13:59:30Z	--- license: apache-2.0 ---
nottrz/InternVL3-14B-4bit-bnb-openai-chat	nottrz	2025-08-18T14:21:59Z	0	0	transformers	[ "transformers", "safetensors", "internvl_chat", "feature-extraction", "internvl", "custom_code", "image-text-to-text", "conversational", "multilingual", "dataset:OpenGVLab/MMPR-v1.2", "arxiv:2312.14238", "arxiv:2404.16821", "arxiv:2412.05271", "arxiv:2411.10442", "arxiv:2504.10479", "arxiv:2412.09616", "base_model:OpenGVLab/InternVL3-14B-Instruct", "base_model:finetune:OpenGVLab/InternVL3-14B-Instruct", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]	image-text-to-text	2025-08-18T14:18:35Z	--- license: apache-2.0 license_name: qwen license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE pipeline_tag: image-text-to-text library_name: transformers base_model: - OpenGVLab/InternVL3-14B-Instruct base_model_relation: finetune datasets: - OpenGVLab/MMPR-v1.2 language: - multilingual tags: - internvl - custom_code --- Disclaimer: Quantized Version with Custom Chat Template This model is a 4-bit NF4 quantized version of `OpenGVLab/InternVL3-14B`, processed using the BitsAndBytes library. The primary modifications are: 1. Quantization: Weights are quantized to 4-bit using NF4. 2. Chat Template: The tokenizer's chat template has been updated to be compatible with OpenAI's multimodal message format (using `<image>` token for InternVL compatibility) and to handle tool/function calls as specified. Please refer to the original model card below for details about the base model's architecture, training, and intended use cases. All credit for the original model architecture and weights goes to the authors of `OpenGVLab/InternVL3-14B`. --- The section below is the original README content from OpenGVLab/InternVL3-14B. --- # InternVL3-14B [\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggingface.co/papers/2411.10442) [\[📜 InternVL3\]](https://huggingface.co/papers/2504.10479) [\[🆕 Blog\]](https://internvl.github.io/blog/) [\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/) [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[🚀 Quick Start\]](#quick-start) [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/) <div align="center"> <img width="500" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/64006c09330a45b03605bba3/zJsd2hqd3EevgXo6fNgC-.png"> </div> ## Introduction We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more. Additionally, we compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/overall.png) ## InternVL3 Family In the following table, we provide an overview of the InternVL3 series. \| Model Name \| Vision Part \| Language Part \| HF Link \| \| :-----------: \| :-------------------------------------------------------------------------------------: \| :----------------------------------------------------------------------------: \| :------------------------------------------------------: \| \| InternVL3-1B \| [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) \| [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-1B) \| \| InternVL3-2B \| [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) \| [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-2B) \| \| InternVL3-8B \| [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) \| [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-8B) \| \| InternVL3-9B \| [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) \| [internlm3-8b-instruct](https://huggingface.co/internlm/internlm3-8b-instruct) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-9B) \| \| InternVL3-14B \| [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) \| [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-14B) \| \| InternVL3-38B \| [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) \| [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-38B) \| \| InternVL3-78B \| [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) \| [Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) \| [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-78B) \| ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/overall-table.png) ## Model Architecture As shown in the following figure, [InternVL3](https://internvl.github.io/blog/2025-04-11-InternVL-3/) retains the same model architecture as [InternVL 2.5](https://internvl.github.io/blog/2024-12-05-InternVL-2.5/) and its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 3 and Qwen 2.5, using a randomly initialized MLP projector. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/BiiyXN6NOk0p-3rl3ueyL.png) As in the previous version, we applied a pixel unshuffle operation, reducing the number of visual tokens to one-quarter of the original. Besides, we adopted a similar dynamic resolution strategy as InternVL 1.5, dividing images into tiles of 448×448 pixels. The key difference, starting from InternVL 2.0, is that we additionally introduced support for multi-image and video data. Notably, in InternVL3, we integrate the [Variable Visual Position Encoding (V2PE)](https://arxiv.org/abs/2412.09616), which utilizes smaller, more flexible position increments for visual tokens. Benefiting from V2PE, InternVL3 exhibits better long context understanding capabilities compared to its predecessors. ## Training Strategy ### Native Multimodal Pre-Training We propose a [Native Multimodal Pre-Training](https://huggingface.co/papers/2504.10479) approach that consolidates language and vision learning into a single pre-training stage. In contrast to standard paradigms that first train a language-only model and subsequently adapt it to handle additional modalities, our method interleaves multimodal data (e.g., image-text, video-text, or image-text interleaved sequences) with large-scale textual corpora. This unified training scheme allows the model to learn both linguistic and multimodal representations simultaneously, ultimately enhancing its capability to handle vision-language tasks without the need for separate alignment or bridging modules. Please see [our paper](https://huggingface.co/papers/2504.10479) for more details. ### Supervised Fine-Tuning In this phase, the techniques of random JPEG compression, square loss re-weighting, and multimodal data packing proposed in [InternVL2.5](https://arxiv.org/abs/2412.05271) are also employed in the InternVL3 series. The main advancement of the SFT phase in InternVL3 compared to InternVL2.5 lies in the use of higher-quality and more diverse training data. Specifically, we further extend training samples for tool use, 3D scene understanding, GUI operations, long context tasks, video understanding, scientific diagrams, creative writing, and multimodal reasoning. ### Mixed Preference Optimization During Pre-training and SFT, the model is trained to predict the next token conditioned on previous ground-truth tokens. However, during inference, the model predicts each token based on its own prior outputs. This discrepancy between ground-truth tokens and model-predicted tokens introduces a distribution shift, which can impair the model’s Chain-of-Thought (CoT) reasoning capabilities. To mitigate this issue, we employ [MPO](https://arxiv.org/abs/2411.10442), which introduces additional supervision from both positive and negative samples to align the model response distribution with the ground-truth distribution, thereby improving reasoning performance. Specifically, the training objective of MPO is a combination of preference loss \\(\mathcal{L}_{\text{p}}\\), quality loss \\(\mathcal{L}_{\text{q}}\\), and generation loss \\(\mathcal{L}_{\text{g}}\\), which can be formulated as follows: $$ \mathcal{L}=w_{p}\cdot\mathcal{L}_{\text{p}} + w_{q}\cdot\mathcal{L}_{\text{q}} + w_{g}\cdot\mathcal{L}_{\text{g}}, $$ where \\(w_{}\\) represents the weight assigned to each loss component. Please see [our paper](https://arxiv.org/abs/2411.10442) for more details about MPO. ### Test-Time Scaling Test-Time Scaling has been shown to be an effective method to enhance the reasoning abilities of LLMs and MLLMs. In this work, we use the Best-of-N evaluation strategy and employ [VisualPRM-8B](https://huggingface.co/OpenGVLab/VisualPRM-8B) as the critic model to select the best response for reasoning and mathematics evaluation. ## Evaluation on Multimodal Capability ### Multimodal Reasoning and Mathematics ![image/png](https://huggingface.co/OpenGVLab/VisualPRM-8B-v1_1/resolve/main/visualprm-performance.png) ### OCR, Chart, and Document Understanding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/ocr.png) ### Multi-Image & Real-World Comprehension ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/multi-images.png) ### Comprehensive Multimodal & Hallucination Evaluation ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/comprehensive.png) ### Visual Grounding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/grounding.png) ### Multimodal Multilingual Understanding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/multilingual.png) ### Video Understanding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/video.png) ### GUI Grounding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/gui.png) ### Spatial Reasoning ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/vsi.png) ## Evaluation on Language Capability We compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series. Please note that the evaluation scores of Qwen2.5 series may differ from those officially reported, as we have adopted the prompt versions provided in the table across all datasets for OpenCompass evaluation. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/text.png) ## Ablation Study ### Native Multimodal Pre-Training We conduct experiments on the InternVL2-8B model while keeping its architecture, initialization parameters, and training data entirely unchanged. Traditionally, InternVL2-8B employs a training pipeline that begins with an MLP warmup phase for feature alignment followed by an Instruction Tuning stage. In our experiments, we substitute the conventional MLP warmup phase with a native multimodal pre-training process. This modification isolates the contribution of native multimodal pre-training to the overall multimodal capability of the model. The evaluation results in the Figure below shows that the model with native multimodal pre-training exhibits performance on most benchmarks that is comparable to the fully multi-stage-trained InternVL2-8B baseline. Furthermore, when followed by instruction tuning on higher-quality data, the model demonstrates further performance gains across evaluated multimodal tasks. These findings underscore the efficiency of native multimodal pre-training in imparting powerful multimodal capabilities to MLLMs. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/ablation-native.png) ### Mixed Preference Optimization As shown in the table below, models fine-tuned with MPO demonstrate superior reasoning performance across seven multimodal reasoning benchmarks compared to their counterparts without MPO. Specifically, InternVL3-78B and InternVL3-38B outperform their counterparts by 4.1 and 4.5 points, respectively. Notably, the training data used for MPO is a subset of that used for SFT, indicating that the performance improvements primarily stem from the training algorithm rather than the training data. ![image/png](https://huggingface.co/datasets/OpenGVLab/MMPR-v1.2-prompts/resolve/main/ablation-mpo.png) ### Variable Visual Position Encoding As reported in the table below, the introduction of V2PE leads to significant performance gains across most evaluation metrics. In addition, our ablation studies—by varying the positional increment \\( \delta \\)—reveal that even for tasks primarily involving conventional contexts, relatively small \\( \delta \\) values can achieve optimal performance. These findings provide important insights for future efforts aimed at refining position encoding strategies for visual tokens in MLLMs. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/ablation-v2pe.png) ## Quick Start We provide an example code to run `InternVL3-14B` using `transformers`. > Please use transformers>=4.37.2 to ensure the model works normally. ### Model Loading #### 16-bit (bf16 / fp16) ```python import torch from transformers import AutoTokenizer, AutoModel path = "OpenGVLab/InternVL3-14B" model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True).eval().cuda() ``` #### BNB 8-bit Quantization ```python import torch from transformers import AutoTokenizer, AutoModel path = "OpenGVLab/InternVL3-14B" model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, load_in_8bit=True, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True).eval() ``` #### Multiple GPUs The reason for writing the code this way is to avoid errors that occur during multi-GPU inference due to tensors not being on the same device. By ensuring that the first and last layers of the large language model (LLM) are on the same device, we prevent such errors. ```python import math import torch from transformers import AutoTokenizer, AutoModel def split_model(model_name): device_map = {} world_size = torch.cuda.device_count() config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) num_layers = config.llm_config.num_hidden_layers # Since the first GPU will be used for ViT, treat it as half a GPU. num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5)) num_layers_per_gpu = [num_layers_per_gpu] world_size num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5) layer_cnt = 0 for i, num_layer in enumerate(num_layers_per_gpu): for j in range(num_layer): device_map[f'language_model.model.layers.{layer_cnt}'] = i layer_cnt += 1 device_map['vision_model'] = 0 device_map['mlp1'] = 0 device_map['language_model.model.tok_embeddings'] = 0 device_map['language_model.model.embed_tokens'] = 0 device_map['language_model.output'] = 0 device_map['language_model.model.norm'] = 0 device_map['language_model.model.rotary_emb'] = 0 device_map['language_model.lm_head'] = 0 device_map[f'language_model.model.layers.{num_layers - 1}'] = 0 return device_map path = "OpenGVLab/InternVL3-14B" device_map = split_model('InternVL3-14B') model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True, device_map=device_map).eval() ``` ### Inference with Transformers ```python import math import numpy as np import torch import torchvision.transforms as T from decord import VideoReader, cpu from PIL import Image from torchvision.transforms.functional import InterpolationMode from transformers import AutoModel, AutoTokenizer IMAGENET_MEAN = (0.485, 0.456, 0.406) IMAGENET_STD = (0.229, 0.224, 0.225) def build_transform(input_size): MEAN, STD = IMAGENET_MEAN, IMAGENET_STD transform = T.Compose([ T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img), T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC), T.ToTensor(), T.Normalize(mean=MEAN, std=STD) ]) return transform def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size): best_ratio_diff = float('inf') best_ratio = (1, 1) area = width * height for ratio in target_ratios: target_aspect_ratio = ratio[0] / ratio[1] ratio_diff = abs(aspect_ratio - target_aspect_ratio) if ratio_diff < best_ratio_diff: best_ratio_diff = ratio_diff best_ratio = ratio elif ratio_diff == best_ratio_diff: if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]: best_ratio = ratio return best_ratio def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False): orig_width, orig_height = image.size aspect_ratio = orig_width / orig_height # calculate the existing image aspect ratio target_ratios = set( (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if i * j <= max_num and i * j >= min_num) target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1]) # find the closest aspect ratio to the target target_aspect_ratio = find_closest_aspect_ratio( aspect_ratio, target_ratios, orig_width, orig_height, image_size) # calculate the target width and height target_width = image_size * target_aspect_ratio[0] target_height = image_size * target_aspect_ratio[1] blocks = target_aspect_ratio[0] * target_aspect_ratio[1] # resize the image resized_img = image.resize((target_width, target_height)) processed_images = [] for i in range(blocks): box = ( (i % (target_width // image_size)) * image_size, (i // (target_width // image_size)) * image_size, ((i % (target_width // image_size)) + 1) * image_size, ((i // (target_width // image_size)) + 1) * image_size ) # split the image split_img = resized_img.crop(box) processed_images.append(split_img) assert len(processed_images) == blocks if use_thumbnail and len(processed_images) != 1: thumbnail_img = image.resize((image_size, image_size)) processed_images.append(thumbnail_img) return processed_images def load_image(image_file, input_size=448, max_num=12): image = Image.open(image_file).convert('RGB') transform = build_transform(input_size=input_size) images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num) pixel_values = [transform(image) for image in images] pixel_values = torch.stack(pixel_values) return pixel_values def split_model(model_name): device_map = {} world_size = torch.cuda.device_count() config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) num_layers = config.llm_config.num_hidden_layers # Since the first GPU will be used for ViT, treat it as half a GPU. num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5)) num_layers_per_gpu = [num_layers_per_gpu] * world_size num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5) layer_cnt = 0 for i, num_layer in enumerate(num_layers_per_gpu): for j in range(num_layer): device_map[f'language_model.model.layers.{layer_cnt}'] = i layer_cnt += 1 device_map['vision_model'] = 0 device_map['mlp1'] = 0 device_map['language_model.model.tok_embeddings'] = 0 device_map['language_model.model.embed_tokens'] = 0 device_map['language_model.output'] = 0 device_map['language_model.model.norm'] = 0 device_map['language_model.model.rotary_emb'] = 0 device_map['language_model.lm_head'] = 0 device_map[f'language_model.model.layers.{num_layers - 1}'] = 0 return device_map # If you set `load_in_8bit=True`, you will need two 80GB GPUs. # If you set `load_in_8bit=False`, you will need at least three 80GB GPUs. path = 'OpenGVLab/InternVL3-14B' device_map = split_model('InternVL3-14B') model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, load_in_8bit=False, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True, device_map=device_map).eval() tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False) # set the max number of tiles in `max_num` pixel_values = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() generation_config = dict(max_new_tokens=1024, do_sample=True) # pure-text conversation (纯文本对话) question = 'Hello, who are you?' response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'Can you tell me a story?' response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # single-image single-round conversation (单图单轮对话) question = '<image>\nPlease describe the image shortly.' response = model.chat(tokenizer, pixel_values, question, generation_config) print(f'User: {question}\nAssistant: {response}') # single-image multi-round conversation (单图多轮对话) question = '<image>\nPlease describe the image in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'Please write a poem according to the image.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # multi-image multi-round conversation, combined images (多图多轮对话，拼接图像) pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0) question = '<image>\nDescribe the two images in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'What are the similarities and differences between these two images.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # multi-image multi-round conversation, separate images (多图多轮对话，独立图像) pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0) num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)] question = 'Image-1: <image>\nImage-2: <image>\nDescribe the two images in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'What are the similarities and differences between these two images.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # batch inference, single image per sample (单图批处理) pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda() num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)] pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0) questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list) responses = model.batch_chat(tokenizer, pixel_values, num_patches_list=num_patches_list, questions=questions, generation_config=generation_config) for question, response in zip(questions, responses): print(f'User: {question}\nAssistant: {response}') # video multi-round conversation (视频多轮对话) def get_index(bound, fps, max_frame, first_idx=0, num_segments=32): if bound: start, end = bound[0], bound[1] else: start, end = -100000, 100000 start_idx = max(first_idx, round(start * fps)) end_idx = min(round(end * fps), max_frame) seg_size = float(end_idx - start_idx) / num_segments frame_indices = np.array([ int(start_idx + (seg_size / 2) + np.round(seg_size * idx)) for idx in range(num_segments) ]) return frame_indices def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32): vr = VideoReader(video_path, ctx=cpu(0), num_threads=1) max_frame = len(vr) - 1 fps = float(vr.get_avg_fps()) pixel_values_list, num_patches_list = [], [] transform = build_transform(input_size=input_size) frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments) for frame_index in frame_indices: img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB') img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num) pixel_values = [transform(tile) for tile in img] pixel_values = torch.stack(pixel_values) num_patches_list.append(pixel_values.shape[0]) pixel_values_list.append(pixel_values) pixel_values = torch.cat(pixel_values_list) return pixel_values, num_patches_list video_path = './examples/red-panda.mp4' pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1) pixel_values = pixel_values.to(torch.bfloat16).cuda() video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))]) question = video_prefix + 'What is the red panda doing?' # Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{question} response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'Describe this video in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') ``` #### Streaming Output Besides this method, you can also use the following code to get streamed output. ```python from transformers import TextIteratorStreamer from threading import Thread # Initialize the streamer streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True, timeout=10) # Define the generation configuration generation_config = dict(max_new_tokens=1024, do_sample=False, streamer=streamer) # Start the model chat in a separate thread thread = Thread(target=model.chat, kwargs=dict( tokenizer=tokenizer, pixel_values=pixel_values, question=question, history=None, return_history=False, generation_config=generation_config, )) thread.start() # Initialize an empty string to store the generated text generated_text = '' # Loop through the streamer to get the new text as it is generated for new_text in streamer: if new_text == model.conv_template.sep: break generated_text += new_text print(new_text, end='', flush=True) # Print each new chunk of generated text on the same line ``` ## Finetune Many repositories now support fine-tuning of the InternVL series models, including [InternVL](https://github.com/OpenGVLab/InternVL), [SWIFT](https://github.com/modelscope/ms-swift), [XTurner](https://github.com/InternLM/xtuner), and others. Please refer to their documentation for more details on fine-tuning. ## Deployment ### LMDeploy LMDeploy is a toolkit for compressing, deploying, and serving LLMs & VLMs. ```sh # if lmdeploy<0.7.3, you need to explicitly set chat_template_config=ChatTemplateConfig(model_name='internvl2_5') pip install lmdeploy>=0.7.3 ``` LMDeploy abstracts the complex inference process of multi-modal Vision-Language Models (VLM) into an easy-to-use pipeline, similar to the Large Language Model (LLM) inference pipeline. #### A 'Hello, world' Example ```python from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig from lmdeploy.vl import load_image model = 'OpenGVLab/InternVL3-14B' image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg') pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) response = pipe(('describe this image', image)) print(response.text) ``` If `ImportError` occurs while executing this case, please install the required dependency packages as prompted. #### Multi-images Inference When dealing with multiple images, you can put them all in one list. Keep in mind that multiple images will lead to a higher number of input tokens, and as a result, the size of the context window typically needs to be increased. ```python from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig from lmdeploy.vl import load_image from lmdeploy.vl.constants import IMAGE_TOKEN model = 'OpenGVLab/InternVL3-14B' pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) image_urls=[ 'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg', 'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg' ] images = [load_image(img_url) for img_url in image_urls] # Numbering images improves multi-image conversations response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images)) print(response.text) ``` #### Batch Prompts Inference Conducting inference with batch prompts is quite straightforward; just place them within a list structure: ```python from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig from lmdeploy.vl import load_image model = 'OpenGVLab/InternVL3-14B' pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) image_urls=[ "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg", "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg" ] prompts = [('describe this image', load_image(img_url)) for img_url in image_urls] response = pipe(prompts) print(response) ``` #### Multi-turn Conversation There are two ways to do the multi-turn conversations with the pipeline. One is to construct messages according to the format of OpenAI and use above introduced method, the other is to use the `pipeline.chat` interface. ```python from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig, ChatTemplateConfig from lmdeploy.vl import load_image model = 'OpenGVLab/InternVL3-14B' pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg') gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8) sess = pipe.chat(('describe this image', image), gen_config=gen_config) print(sess.response.text) sess = pipe.chat('What is the woman doing?', session=sess, gen_config=gen_config) print(sess.response.text) ``` #### Service LMDeploy's `api_server` enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup: ```shell lmdeploy serve api_server OpenGVLab/InternVL3-14B --chat-template internvl2_5 --server-port 23333 --tp 1 ``` To use the OpenAI-style interface, you need to install OpenAI: ```shell pip install openai ``` Then, use the code below to make the API call: ```python from openai import OpenAI client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1') model_name = client.models.list().data[0].id response = client.chat.completions.create( model=model_name, messages=[{ 'role': 'user', 'content': [{ 'type': 'text', 'text': 'describe this image', }, { 'type': 'image_url', 'image_url': { 'url': 'https://modelscope.oss-cn-beijing.aliyuncs.com/resource/tiger.jpeg', }, }], }], temperature=0.8, top_p=0.8) print(response) ``` ## License This project is released under the MIT License. This project uses the pre-trained Qwen2.5 as a component, which is licensed under the Apache-2.0 License. ## Citation If you find this project useful in your research, please consider citing: ```BibTeX @article{chen2024expanding, title={Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling}, author={Chen, Zhe and Wang, Weiyun and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Cui, Erfei and Zhu, Jinguo and Ye, Shenglong and Tian, Hao and Liu, Zhaoyang and others}, journal={arXiv preprint arXiv:2412.05271}, year={2024} } @article{wang2024mpo, title={Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization}, author={Wang, Weiyun and Chen, Zhe and Wang, Wenhai and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Zhu, Jinguo and Zhu, Xizhou and Lu, Lewei and Qiao, Yu and Dai, Jifeng}, journal={arXiv preprint arXiv:2411.10442}, year={2024} } @article{chen2024far, title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites}, author={Chen, Zhe and Wang, Weiyun and Tian, Hao and Ye, Shenglong and Gao, Zhangwei and Cui, Erfei and Tong, Wenwen and Hu, Kongzhi and Luo, Jiapeng and Ma, Zheng and others}, journal={arXiv preprint arXiv:2404.16821}, year={2024} } @inproceedings{chen2024internvl, title={Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks}, author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and others}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={24185--24198}, year={2024} } ```
cicboy/my_awesome_qa_model	cicboy	2025-08-18T14:20:45Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2025-08-18T09:49:04Z	--- library_name: transformers license: apache-2.0 base_model: distilbert/distilbert-base-uncased tags: - generated_from_trainer model-index: - name: my_awesome_qa_model results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_qa_model This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1538 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.2139 \| 1.0 \| 5475 \| 1.1628 \| \| 0.9801 \| 2.0 \| 10950 \| 1.1107 \| \| 0.7503 \| 3.0 \| 16425 \| 1.1538 \| ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4
ench100/bodyandface	ench100	2025-08-18T14:18:21Z	59	1	diffusers	[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:lodestones/Chroma", "base_model:adapter:lodestones/Chroma", "region:us" ]	text-to-image	2025-08-12T08:58:41Z	--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - output: url: images/2.png text: '-' base_model: lodestones/Chroma instance_prompt: null --- # forME <Gallery /> ## Download model [Download](/ench100/bodyandface/tree/main) them in the Files & versions tab.
WaiLwin/topology_results	WaiLwin	2025-08-18T14:18:07Z	0	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-08-18T14:17:52Z	--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: topology_results results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # topology_results This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0109 - Accuracy: 0.9977 - F1: 0.9977 - Precision: 0.9977 - Recall: 0.9977 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 10 - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| Precision \| Recall \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\| \| 0.0003 \| 1.0 \| 1004 \| 0.0130 \| 0.9977 \| 0.9977 \| 0.9977 \| 0.9977 \| \| 0.0001 \| 2.0 \| 2008 \| 0.0158 \| 0.9965 \| 0.9965 \| 0.9965 \| 0.9965 \| \| 0.0001 \| 3.0 \| 3012 \| 0.0036 \| 0.9988 \| 0.9988 \| 0.9988 \| 0.9988 \| ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4
BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o	BootesVoid	2025-08-18T14:09:52Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-08-18T14:09:51Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: RUBIO0808 --- # Cmeh250Ii0O6Srts8J6939U0N_Cmeh53Idu0Objrts8Tgpz0O5O <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `RUBIO0808` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "RUBIO0808", "lora_weights": "https://huggingface.co/BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o', weight_name='lora.safetensors') image = pipeline('RUBIO0808').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o/discussions) to add images that show off what you’ve made with this LoRA.
JWHaHa/Qwen2.5-7B-Instruct-SCGF-GGUF	JWHaHa	2025-08-18T14:06:36Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-08-18T14:06:23Z	--- base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: JWHaHa - License: apache-2.0 - Finetuned from model : unsloth/qwen2.5-7b-instruct-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
inclusionAI/GroveMoE-Inst	inclusionAI	2025-08-18T14:06:10Z	0	7	transformers	[ "transformers", "safetensors", "qwen3_moe", "text-generation", "conversational", "custom_code", "arxiv:2508.07785", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T05:28:51Z	--- library_name: transformers license: apache-2.0 pipeline_tag: text-generation --- # GroveMoE-Inst ## Highlights We introduce GroveMoE, a new sparse architecture using adjugate experts for dynamic computation allocation, featuring the following key highlights: - Architecture: Novel adjugate experts grouped with ordinary experts; shared computation is executed once, then reused, cutting FLOPs. - Sparse Activation: 33 B params total, only 3.14–3.28 B active per token. - Traning: Mid-training + SFT, up-cycled from Qwen3-30B-A3B-Base; preserves prior knowledge while adding new capabilities. ## Model Downloads \| Model \| #Total Params \| #Activated Params \| Download \| \|:---------:\|:-----------------:\|:---------------------:\|:------------:\| \| GroveMoE-Base \| 33B \| 3.14~3.28B \| [🤗 HuggingFace](https://huggingface.co/inclusionAI/GroveMoE-Base) \| \| GroveMoE-Inst \| 33B \| 3.14~3.28B \| [🤗 HuggingFace](https://huggingface.co/inclusionAI/GroveMoE-Inst) \| ## Performance \| Model \| Activated Params \| MMLU-Pro \| SuperGPQA \| GPQA-Diamond \| OlympiadBench \| Omni-math \| AIME'25 \| MultiPL-E \| LiveCodeBench v6 \| \|:-----:\|:----------------:\|:------------:\|:-------------:\|:------------:\|:-----------------:\|:------------:\|:------------------:\|:------------------:\|:------------------:\| \|Llama4-Scout\| 17B \| 64.9 \| 42.0 \| 55.6 \| 56.6 \| 30.2 \| 10.0 \| 45.0 \| 32.0 \| \|Qwen3-30B-A3B\| 3B \| 63.3 \| 40.5 \| 51.7 \| 60.3 \| 33.7 \| 21.7 \| 66.0 \| 29.4 \| \|Qwen3-32B\| 32B \| 68.2 \| 43.0 \| 53.6 \| 59.5 \| 31.8 \| 22.9 \| 68.6 \| 28.6 \| \|Gemma3-27B-IT\| 27B \| 67.1 \| 35.6 \| 45.3 \| 59.9 \| 33.3 \| 23.1 \| 65.5 \| 30.9 \| \|Mistral-Small-3.2\| 24B \| 68.1 \| 37.5 \| 59.9 \| 61.9 \| 33.4 \| 28.1 \| 69.5 \| 32.2 \| \|GroveMoE-Inst\|3.14~3.28B \| <font color=#FBD98D>72.8</font> \| <font color=#FBD98D>47.7</font> \| <font color=#FBD98D>61.3</font> \|<font color=#FBD98D>71.2</font> \|<font color=#FBD98D>43.5</font> \| <font color=#FBD98D>44.4</font> \|<font color=#FBD98D>74.5</font> \| <font color=#FBD98D>34.6</font> \| We bold the top1 scores separately for all models. More details are reported in our [technical report](https://arxiv.org/abs/2508.07785). ## Usage Below, there are some code snippets on how to get quickly started with running the model. First, install the Transformers library. ```sh $ pip install transformers==4.51.3 ``` Then, copy the snippet from the section that is relevant for your use case. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "inclusionAI/GroveMoE-Inst" # load the tokenizer and the model tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) # prepare the model input prompt = "Give me a short introduction to large language model." messages = [ {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completion generated_ids = model.generate( **model_inputs, max_new_tokens=16384 ) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() content = tokenizer.decode(output_ids, skip_special_tokens=True) print("content:", content) ``` ## Citation ```bibtex @article{GroveMoE, title = {GroveMoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts}, author = {Wu, Haoyuan and Chen, Haoxing and Chen, Xiaodong and Zhou, Zhanchao and Chen, Tieyuan and Zhuang, Yihong and Lu, Guoshan and Zhao, Junbo and Liu, Lin and Huang, Zenan and Lan, Zhenzhong and Yu, Bei and Li, Jianguo}, journal = {arXiv preprint arXiv:2508.07785}, year = {2025} } ```
moscowx21/blockassist-bc-extinct_bipedal_clam_1755525846	moscowx21	2025-08-18T14:04:52Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "extinct bipedal clam", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T14:04:43Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - extinct bipedal clam --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF	zehuajun	2025-08-18T14:01:37Z	0	0	transformers	[ "transformers", "gguf", "abliterated", "uncensored", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated", "base_model:quantized:huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated", "license:apache-2.0", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T14:00:22Z	--- license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE language: - en base_model: huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated pipeline_tag: text-generation library_name: transformers tags: - abliterated - uncensored - llama-cpp - gguf-my-repo --- # zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF This model was converted to GGUF format from [`huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated`](https://huggingface.co/huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -c 2048 ```
BinBashir/roberta_on_jumia_dataset	BinBashir	2025-08-18T13:57:48Z	0	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-08-18T13:57:25Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
chainway9/blockassist-bc-untamed_quick_eel_1755523556	chainway9	2025-08-18T13:54:47Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "untamed quick eel", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T13:54:43Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - untamed quick eel --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
ghofrani/xls-r-1b-fa-cv8	ghofrani	2025-08-18T13:54:37Z	56	2	transformers	[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "mozilla-foundation/common_voice_8_0", "generated_from_trainer", "fa", "dataset:common_voice", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2022-03-02T23:29:05Z	--- language: - fa tags: - automatic-speech-recognition - mozilla-foundation/common_voice_8_0 - generated_from_trainer datasets: - common_voice model-index: - name: common8 results: [] license: apache-2.0 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # common8 This model is a fine-tuned version of [wghts/checkpoint-20000](https://huggingface.co/wghts/checkpoint-20000) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - FA dataset. It achieves the following results on the evaluation set: - Loss: 0.3174 - Wer: 0.3022 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 32 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 6 - total_train_batch_size: 192 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 250.0 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:------:\| \| 3.5847 \| 1.93 \| 500 \| 3.5104 \| 1.0 \| \| 2.7858 \| 3.86 \| 1000 \| 2.9601 \| 1.0001 \| \| 1.6827 \| 5.79 \| 1500 \| 0.7853 \| 0.7030 \| \| 1.4656 \| 7.72 \| 2000 \| 0.6076 \| 0.6014 \| \| 1.3693 \| 9.65 \| 2500 \| 0.5114 \| 0.5307 \| \| 1.379 \| 11.58 \| 3000 \| 0.4666 \| 0.4940 \| \| 1.2832 \| 13.51 \| 3500 \| 0.4257 \| 0.4593 \| \| 1.1931 \| 15.44 \| 4000 \| 0.4039 \| 0.4427 \| \| 1.2911 \| 17.37 \| 4500 \| 0.3956 \| 0.4295 \| \| 1.1577 \| 19.3 \| 5000 \| 0.3705 \| 0.4114 \| \| 1.1135 \| 21.24 \| 5500 \| 0.3740 \| 0.4010 \| \| 1.19 \| 23.17 \| 6000 \| 0.3611 \| 0.3935 \| \| 1.1008 \| 25.1 \| 6500 \| 0.3503 \| 0.3880 \| \| 1.0805 \| 27.03 \| 7000 \| 0.3427 \| 0.3781 \| \| 1.1556 \| 28.96 \| 7500 \| 0.3442 \| 0.3727 \| \| 1.0596 \| 30.89 \| 8000 \| 0.3398 \| 0.3646 \| \| 1.0219 \| 32.82 \| 8500 \| 0.3312 \| 0.3660 \| \| 1.1042 \| 34.75 \| 9000 \| 0.3287 \| 0.3612 \| \| 1.0273 \| 36.68 \| 9500 \| 0.3236 \| 0.3556 \| \| 1.0383 \| 38.61 \| 10000 \| 0.3217 \| 0.3558 \| \| 1.0498 \| 40.54 \| 10500 \| 0.3205 \| 0.3520 \| \| 0.9969 \| 42.47 \| 11000 \| 0.3125 \| 0.3504 \| \| 1.0658 \| 44.4 \| 11500 \| 0.3120 \| 0.3493 \| \| 0.992 \| 46.33 \| 12000 \| 0.3137 \| 0.3476 \| \| 0.9737 \| 48.26 \| 12500 \| 0.3085 \| 0.3413 \| \| 1.0817 \| 50.19 \| 13000 \| 0.3091 \| 0.3418 \| \| 0.9414 \| 52.12 \| 13500 \| 0.3072 \| 0.3344 \| \| 0.9295 \| 54.05 \| 14000 \| 0.3039 \| 0.3322 \| \| 1.0248 \| 55.98 \| 14500 \| 0.2991 \| 0.3325 \| \| 0.9474 \| 57.91 \| 15000 \| 0.3032 \| 0.3348 \| \| 0.928 \| 59.85 \| 15500 \| 0.2999 \| 0.3285 \| \| 1.0321 \| 61.78 \| 16000 \| 0.2982 \| 0.3253 \| \| 0.9255 \| 63.71 \| 16500 \| 0.2970 \| 0.3231 \| \| 0.8928 \| 65.64 \| 17000 \| 0.2993 \| 0.3250 \| \| 1.008 \| 67.57 \| 17500 \| 0.2985 \| 0.3222 \| \| 0.9371 \| 69.5 \| 18000 \| 0.2968 \| 0.3216 \| \| 0.9077 \| 71.43 \| 18500 \| 0.3011 \| 0.3299 \| \| 1.0044 \| 73.36 \| 19000 \| 0.3053 \| 0.3306 \| \| 0.9625 \| 75.29 \| 19500 \| 0.3159 \| 0.3295 \| \| 0.9816 \| 77.22 \| 20000 \| 0.3080 \| 0.3304 \| \| 0.9587 \| 119.19 \| 20500 \| 0.3088 \| 0.3284 \| \| 0.9178 \| 122.09 \| 21000 \| 0.3132 \| 0.3320 \| \| 1.0282 \| 125.0 \| 21500 \| 0.3099 \| 0.3266 \| \| 0.9337 \| 127.9 \| 22000 \| 0.3110 \| 0.3317 \| \| 0.8822 \| 130.81 \| 22500 \| 0.3037 \| 0.3247 \| \| 0.9644 \| 133.72 \| 23000 \| 0.3037 \| 0.3238 \| \| 0.9214 \| 136.62 \| 23500 \| 0.3040 \| 0.3234 \| \| 0.9167 \| 139.53 \| 24000 \| 0.3079 \| 0.3203 \| \| 0.9047 \| 142.44 \| 24500 \| 0.3018 \| 0.3177 \| \| 0.8909 \| 145.35 \| 25000 \| 0.3053 \| 0.3181 \| \| 0.9646 \| 148.25 \| 25500 \| 0.3095 \| 0.3229 \| \| 0.8802 \| 151.16 \| 26000 \| 0.3111 \| 0.3192 \| \| 0.8411 \| 154.07 \| 26500 \| 0.3068 \| 0.3123 \| \| 0.9235 \| 156.97 \| 27000 \| 0.3090 \| 0.3177 \| \| 0.8943 \| 159.88 \| 27500 \| 0.3115 \| 0.3179 \| \| 0.8854 \| 162.79 \| 28000 \| 0.3052 \| 0.3157 \| \| 0.8734 \| 165.69 \| 28500 \| 0.3077 \| 0.3124 \| \| 0.8515 \| 168.6 \| 29000 \| 0.3117 \| 0.3128 \| \| 0.912 \| 171.51 \| 29500 \| 0.3039 \| 0.3121 \| \| 0.8669 \| 174.42 \| 30000 \| 0.3120 \| 0.3123 \| \| 0.823 \| 177.32 \| 30500 \| 0.3148 \| 0.3118 \| \| 0.9129 \| 180.23 \| 31000 \| 0.3179 \| 0.3101 \| \| 0.8255 \| 183.14 \| 31500 \| 0.3164 \| 0.3114 \| \| 0.8948 \| 186.05 \| 32000 \| 0.3128 \| 0.3101 \| \| 0.8397 \| 188.95 \| 32500 \| 0.3143 \| 0.3068 \| \| 0.8341 \| 191.86 \| 33000 \| 0.3127 \| 0.3136 \| \| 0.873 \| 194.76 \| 33500 \| 0.3149 \| 0.3124 \| \| 0.8232 \| 197.67 \| 34000 \| 0.3166 \| 0.3086 \| \| 0.8002 \| 200.58 \| 34500 \| 0.3149 \| 0.3061 \| \| 0.8621 \| 203.49 \| 35000 \| 0.3160 \| 0.3093 \| \| 0.8123 \| 206.39 \| 35500 \| 0.3141 \| 0.3063 \| \| 0.7995 \| 209.3 \| 36000 \| 0.3174 \| 0.3075 \| \| 0.8271 \| 212.21 \| 36500 \| 0.3173 \| 0.3043 \| \| 0.8059 \| 215.12 \| 37000 \| 0.3176 \| 0.3079 \| \| 0.8835 \| 218.02 \| 37500 \| 0.3169 \| 0.3062 \| \| 0.8027 \| 220.93 \| 38000 \| 0.3203 \| 0.3098 \| \| 0.775 \| 223.83 \| 38500 \| 0.3159 \| 0.3068 \| \| 0.8487 \| 226.74 \| 39000 \| 0.3161 \| 0.3072 \| \| 0.7929 \| 229.65 \| 39500 \| 0.3143 \| 0.3037 \| \| 0.7653 \| 232.56 \| 40000 \| 0.3160 \| 0.3048 \| \| 0.8211 \| 235.46 \| 40500 \| 0.3173 \| 0.3031 \| \| 0.7761 \| 238.37 \| 41000 \| 0.3176 \| 0.3025 \| \| 0.7761 \| 241.28 \| 41500 \| 0.3179 \| 0.3027 \| \| 0.7903 \| 244.19 \| 42000 \| 0.3181 \| 0.3016 \| \| 0.7807 \| 247.09 \| 42500 \| 0.3170 \| 0.3027 \| \| 0.8406 \| 250.0 \| 43000 \| 0.3174 \| 0.3022 \| ### Framework versions - Transformers 4.17.0.dev0 - Pytorch 1.10.2 - Datasets 1.18.3.dev0 - Tokenizers 0.10.3
mgazz/Prithvi-EO-2.0-300M-BurnScars	mgazz	2025-08-18T13:51:16Z	10	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-08-14T14:05:43Z	--- license: apache-2.0 ---
mookiezi/Discord-Micae-Hermes-3-3B	mookiezi	2025-08-18T13:35:59Z	1,764	2	transformers	[ "transformers", "safetensors", "llama", "text-generation", "causal-lm", "instruct", "chat", "fine-tuned", "merged-lora", "llama-3", "hermes", "discord-dataset", "conversational-ai", "chatml", "pytorch", "open-weights", "3b-parameters", "conversational", "dataset:mookiezi/Discord-OpenMicae", "arxiv:2408.11857", "base_model:NousResearch/Hermes-3-Llama-3.2-3B", "base_model:finetune:NousResearch/Hermes-3-Llama-3.2-3B", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-02T23:21:01Z	--- tags: - transformers - causal-lm - text-generation - instruct - chat - fine-tuned - merged-lora - llama-3 - hermes - discord-dataset - conversational-ai - chatml - pytorch - open-weights - 3b-parameters model-index: - name: Discord-Micae-Hermes-3-3B results: [] base_model: - NousResearch/Hermes-3-Llama-3.2-3B datasets: - mookiezi/Discord-OpenMicae library_name: transformers license: llama3 --- <div style="display: flex; align-items: center; gap: 8px;"> <span>Run this model on Google Colab for free:</span> <a href="https://colab.research.google.com/drive/1kUtTeey5THhKW6f0BDKB9MFe4JIEew_Z?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/> </a> </div> ## Discord-Micae-Hermes-3-3B ![Micae](Micae-Thumb.png) ## Model Description Discord-Micae-Hermes-3-3B is a new finetune on [NousResearch/Hermes-3-Llama-3.2-3B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B). This model serves as a foundation for ongoing exploration into the capabilities of human-adjacent text generation. - Training Schedule: - 17M tokens of 260 thousand single-turn exchanges (STX) – 6 epochs @ 2e-5 - 5.5M tokens of 101 thousand multi-turn chains – 6 epochs @ 2e-5 - Combined dataset – 1 epoch @ 1e-5 - Fine-Tuning Method: LoRA merge (α = 32, r = 8, dropout = 0.1) - LoRA target modules: q_proj, v_proj - Scheduler: Cosine schedule with 220 warmup steps per phase - Optimizer: torch.optim.AdamW (betas = (0.9, 0.999), amsgrad = False, eps = 1e-8, weight decay = 0.01) - Batching: Effective size of 126 (7 batch size × 18 gradient accumulation steps) - Timeline and Hardware: Training took place over 17 days on a GTX 1080 (8GB). ## Dataset The model was fine-tuned on the [mookiezi/Discord-OpenMicae](https://huggingface.co/datasets/mookiezi/Discord-OpenMicae) dataset. ## Intended Use - Conversational AI research - Experimentation with dialogue agents trained on Discord data - Chatbots requiring casual, human-like tone ### Limitations - The model inherits potential biases from Discord-style language. - It is not safety-aligned for deployment without moderation. - While it does inhert knowledge from Hermes-3-3B it is not intended for factual or sensitive information retrieval. ## Prompting Micae uses the same ChatML prompt format as Hermes 3 and handles context and chat history. ``` <\|im_start\|>user what do you think about ai?<\|im_end\|> <\|im_start\|>assistant i'm not a fan of AI but I can understand why people are excited to use it. it's like the first time they got an electric car, or when they were able to fly in space, that excitement is real<\|im_end\|> <\|im_start\|>user where do you think it's heading?<\|im_end\|> <\|im_start\|>assistant it will be used for good and bad things just as with other techs<\|im_end\|> <\|im_start\|>user what do you do use it for personally?<\|im_end\|> <\|im_start\|>assistant nothing much yet, I hope to find some stuff later on.<\|im_end\|> <\|im_start\|>user do you like pokemon?<\|im_end\|> <\|im_start\|>assistant yes I love Pokémon.<\|im_end\|> <\|im_start\|>user what's your favorite pokemon<\|im_end\|> <\|im_start\|>assistant garchomp<\|im_end\|> ``` --- ## Inferfacing A python script for interfacing, optimized for casual, Discord-style conversation, is available at [https://github.com/mookiezi/interface](https://github.com/mookiezi/interface). To use this model run: ``` python interface.py -m mookiezi/Discord-Micae-Hermes-3-3B ``` ![Interface Screenshot](interface-screenshot.png) --- ## License See the [Meta LLaMA 3 Community License](https://ai.meta.com/llama/license/) for details. ## How to cite: If you use this model in your work, please cite both Discord-Micae-Hermes-3-3B and the base model Hermes 3: ```bibtex @misc{discord-micae-hermes3b, title = {Discord-Micae-Hermes-3-3B}, author = {mookiezi}, year = {2025}, url={https://huggingface.co/mookiezi/Discord-Micae-Hermes-3-3B} } @misc{teknium2024hermes3technicalreport, title={Hermes 3 Technical Report}, author={Ryan Teknium and Jeffrey Quesnelle and Chen Guang}, year={2024}, eprint={2408.11857}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2408.11857} } ``` [](https://20000.online/micae) [](https://20000.online/openmicae) [](https://20000.online/discord-dialogues)
thanobidex/blockassist-bc-colorful_shiny_hare_1755522529	thanobidex	2025-08-18T13:34:30Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "colorful shiny hare", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T13:34:26Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - colorful shiny hare --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
pempekmangedd/blockassist-bc-patterned_sturdy_dolphin_1755522494	pempekmangedd	2025-08-18T13:33:42Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "patterned sturdy dolphin", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T13:33:38Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - patterned sturdy dolphin --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
mradermacher/InnoSpark-VPC-RM-32B-GGUF	mradermacher	2025-08-18T13:30:02Z	156	0	transformers	[ "transformers", "gguf", "en", "base_model:sii-research/InnoSpark-HPC-RM-32B", "base_model:quantized:sii-research/InnoSpark-HPC-RM-32B", "license:mit", "endpoints_compatible", "region:us", "conversational" ]	null	2025-07-21T12:05:02Z	--- base_model: sii-research/InnoSpark-HPC-RM-32B language: - en library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/sii-research/InnoSpark-HPC-RM-32B <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InnoSpark-VPC-RM-32B-GGUF).* weighted/imatrix quants are available at https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q2_K.gguf) \| Q2_K \| 12.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q3_K_S.gguf) \| Q3_K_S \| 14.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q3_K_M.gguf) \| Q3_K_M \| 16.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q3_K_L.gguf) \| Q3_K_L \| 17.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.IQ4_XS.gguf) \| IQ4_XS \| 18.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q4_K_S.gguf) \| Q4_K_S \| 18.9 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q4_K_M.gguf) \| Q4_K_M \| 20.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q5_K_S.gguf) \| Q5_K_S \| 22.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q5_K_M.gguf) \| Q5_K_M \| 23.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q6_K.gguf) \| Q6_K \| 27.0 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q8_0.gguf) \| Q8_0 \| 34.9 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/InnoSpark-R-72B-0701-GGUF	mradermacher	2025-08-18T13:28:26Z	129	1	transformers	[ "transformers", "gguf", "en", "base_model:sii-research/InnoSpark-R-72B-0701", "base_model:quantized:sii-research/InnoSpark-R-72B-0701", "license:mit", "endpoints_compatible", "region:us", "conversational" ]	null	2025-07-22T09:53:04Z	--- base_model: sii-research/InnoSpark-R-72B-0701 language: - en library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/sii-research/InnoSpark-R-72B-0701 <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InnoSpark-R-72B-0701-GGUF).* weighted/imatrix quants are available at https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q2_K.gguf) \| Q2_K \| 29.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q3_K_S.gguf) \| Q3_K_S \| 34.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q3_K_M.gguf) \| Q3_K_M \| 37.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q3_K_L.gguf) \| Q3_K_L \| 39.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.IQ4_XS.gguf) \| IQ4_XS \| 40.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q4_K_S.gguf) \| Q4_K_S \| 44.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q4_K_M.gguf) \| Q4_K_M \| 47.5 \| fast, recommended \| \| [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_S.gguf.part2of2) \| Q5_K_S \| 51.5 \| \| \| [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_M.gguf.part2of2) \| Q5_K_M \| 54.5 \| \| \| [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q6_K.gguf.part2of2) \| Q6_K \| 64.4 \| very good quality \| \| [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q8_0.gguf.part2of2) \| Q8_0 \| 77.4 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
ahhava/elyon	ahhava	2025-08-18T13:27:20Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-08-18T13:01:49Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: elyon --- # Elyon <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `elyon` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "elyon", "lora_weights": "https://huggingface.co/ahhava/elyon/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('ahhava/elyon', weight_name='lora.safetensors') image = pipeline('elyon').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 30 ## Contribute your own examples You can use the [community tab](https://huggingface.co/ahhava/elyon/discussions) to add images that show off what you’ve made with this LoRA.
ciorant/checkpoints	ciorant	2025-08-18T13:23:04Z	0	0	transformers	[ "transformers", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-base", "base_model:finetune:facebook/bart-base", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-08-18T13:22:45Z	--- library_name: transformers license: apache-2.0 base_model: facebook/bart-base tags: - generated_from_trainer model-index: - name: checkpoints results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # checkpoints This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 4 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4
zekaemo/Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training	zekaemo	2025-08-18T13:22:02Z	0	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:indobenchmark/indobert-base-p2", "base_model:finetune:indobenchmark/indobert-base-p2", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-08-18T13:12:14Z	--- library_name: transformers license: mit base_model: indobenchmark/indobert-base-p2 tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.8187 - Accuracy: 0.8105263157894737 - F1: 0.8086037151702786 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 15 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| 0.6196 \| 1.0 \| 51 \| 0.4970 \| 0.7719 \| 0.7780 \| \| 0.4067 \| 2.0 \| 102 \| 0.5441 \| 0.7404 \| 0.7495 \| \| 0.2248 \| 3.0 \| 153 \| 0.7342 \| 0.7684 \| 0.7669 \| \| 0.1776 \| 4.0 \| 204 \| 0.6930 \| 0.8 \| 0.8003 \| \| 0.1137 \| 5.0 \| 255 \| 1.1582 \| 0.7789 \| 0.7707 \| \| 0.0868 \| 6.0 \| 306 \| 1.1574 \| 0.8 \| 0.7983 \| \| 0.0609 \| 7.0 \| 357 \| 1.3369 \| 0.7930 \| 0.7871 \| \| 0.0354 \| 8.0 \| 408 \| 1.2317 \| 0.8105 \| 0.8086 \| \| 0.0188 \| 9.0 \| 459 \| 1.7317 \| 0.8 \| 0.7859 \| \| 0.0127 \| 10.0 \| 510 \| 1.6185 \| 0.8035 \| 0.8000 \| \| 0.0155 \| 11.0 \| 561 \| 1.7635 \| 0.7965 \| 0.7903 \| \| 0.0106 \| 12.0 \| 612 \| 1.8325 \| 0.7965 \| 0.7884 \| \| 0.0106 \| 13.0 \| 663 \| 1.8020 \| 0.7930 \| 0.7871 \| \| 0.0101 \| 14.0 \| 714 \| 1.8116 \| 0.7930 \| 0.7871 \| \| 0.0105 \| 15.0 \| 765 \| 1.8187 \| 0.7930 \| 0.7871 \| ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4
halley-ai/gpt-oss-20b-MLX-6bit-gs32	halley-ai	2025-08-18T13:19:24Z	0	1	mlx	[ "mlx", "safetensors", "gpt_oss", "apple-silicon", "metal", "arm64", "6-bit", "group-size-32", "moe", "mpx4", "openai", "halley-ai", "text-generation", "conversational", "en", "ro", "base_model:openai/gpt-oss-20b", "base_model:quantized:openai/gpt-oss-20b", "license:apache-2.0", "region:us" ]	text-generation	2025-08-16T20:14:21Z	--- library_name: mlx pipeline_tag: text-generation inference: false # MLX is macOS-only; HF Inference API won't run it license: apache-2.0 base_model: openai/gpt-oss-20b base_model_relation: quantized language: - en - ro tags: - apple-silicon - metal - arm64 - 6-bit - group-size-32 - moe - mpx4 - openai - halley-ai --- # gpt-oss-20b — MLX 6-bit (group size 32) Summary. This is a 6-bit (Q6) MLX quantization of gpt-oss-20B (sparse Mixture-of-Experts, MPx4). Group size is 32. Built for Apple Silicon with Metal acceleration. - Base model: `openai/gpt-oss-20b` (Apache-2.0) - Quantization: MLX Q6, `q_group_size=32` (some tensors remain FP16 for stability) - Files: MLX weight shards + `config.json`; tokenizer files included for drop-in use - Footprint: ~18.38 GB on disk - Intended use: local inference / research on M-series Macs - Not intended for: safety-critical decisions; outputs may be inaccurate or biased ## Requirements Runs on: Apple Silicon (M1 or newer) with macOS ≥ 13.5 via MLX (Metal). Not supported: Intel macOS / Linux / Windows (use a GGUF build + llama.cpp instead). RAM guidance: 32 GB minimum for Q6 (gs=32). 24 GB MacBook Pro won’t run it. Extra RAM improves headroom. ## How to use (MLX) ```bash pip install mlx-lm transformers ``` ```python # Python API (uses tokenizer bundled with this repo) from mlx_lm import load, generate model, tokenizer = load("halley-ai/gpt-oss-20b-MLX-6bit-gs32") print(generate( model, tokenizer, prompt="Explain the Chudnovsky algorithm to compute π.", max_tokens=256, max_kv_size=512 )) ``` ## Performance (Apple Silicon, real-world) LM Studio / CLI (MLX, Q6 gs=32): ~49–55 tok/s, TTFB ~0.35–0.45 s (≈2k-token responses) – measured on M1 Max 32 GB (short fixed-length runs show lower t/s due to startup overhead). Throughput varies with Mac model, context, and sampler settings. ## Evaluation Perplexity (PPL) streaming evaluation on WikiText-2; window=stride=4096, ~100k tokens, EOS inserted between docs. <table> <thead> <tr><th>Variant</th><th>PPL (ctx=4096)</th></tr> </thead> <tbody> <tr><td>MLX 8-bit (reference)</td><td>10.75</td></tr> <tr><td><strong>MLX 6-bit (gs=32)</strong></td><td><strong>10.46 (−2.7% vs 8-bit/gs64)</strong></td></tr> <tr><td>MLX 5-bit (gs=32)</td><td>11.11 (+3.3% vs 8-bit/gs64, +6.2% vs 6-bit/gs32)</strong></td></tr> <tr><td>MLX 4-bit (gs=32)</td><td>13.70 (+27.4% vs 8-bit/gs64, +31.0% vs 6-bit/gs32)</td></tr> </tbody> </table> Interpretation - MLX 6-bit/gs32: Best of the group; edges out 8-bit/gs64 slightly at a smaller footprint. - MLX 5-bit/gs32: Small, consistent drop vs 6-bit/gs32 and 8-bit/gs64 (~3–6% PPL); strong “fits-16GB” option when GPU buffer limits matter. - MLX 8-bit/gs64: Solid reference; near‑FP16 quality at a larger footprint. - MLX 4-bit/gs32: Trades accuracy for footprint; use when RAM is constrained or throughput is the priority. ## Conversion details (provenance) ```bash python -m mlx_lm convert \ --hf-path openai/gpt-oss-20b \ --mlx-path gpt-oss-20b-mlx-q6-gs32 \ --q-bits 6 --q-group-size 32 -q ``` - Some non-expert tensors (embeddings, norms, router) remain FP16. ## Sibling & reference models - halley-ai/gpt-oss-20b-MLX-5bit-gs32 - halley-ai/gpt-oss-20b-MLX-4bit-gs32 - Reference (8-bit, upstream): lmstudio-community/gpt-oss-20b-MLX-8bit ## Limitations & biases Outputs may be factually wrong or unsafe. Don’t use for medical, legal, or financial decisions without human review. MoE models can be sensitive to prompt wording; prefer explicit instructions and structure. ## License & credits - License: Apache-2.0 (inherits from base model) - Base model: OpenAI gpt-oss-20B - Quantization: Halley AI Lab (MLX Q6, gs=32) - Please cite both the base model and this repository when you use the weights.
isbondarev/gemma_test	isbondarev	2025-08-18T13:06:08Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-08-18T13:05:07Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/Q3-IIJAN-3B-GGUF	mradermacher	2025-08-18T13:00:38Z	1,156	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:djuna-test-lab/Q3-IIJAN-4B", "base_model:quantized:djuna-test-lab/Q3-IIJAN-4B", "endpoints_compatible", "region:us" ]	null	2025-08-12T18:02:47Z	--- base_model: djuna-test-lab/Q3-IIJAN-4B language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/djuna-test-lab/Q3-IIJAN-4B <!-- provided-files --> *For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q3-IIJAN-3B-GGUF).* weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q2_K.gguf) \| Q2_K \| 1.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q3_K_S.gguf) \| Q3_K_S \| 2.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q3_K_M.gguf) \| Q3_K_M \| 2.2 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q3_K_L.gguf) \| Q3_K_L \| 2.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.IQ4_XS.gguf) \| IQ4_XS \| 2.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q4_K_S.gguf) \| Q4_K_S \| 2.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q4_K_M.gguf) \| Q4_K_M \| 2.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q5_K_S.gguf) \| Q5_K_S \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q5_K_M.gguf) \| Q5_K_M \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q6_K.gguf) \| Q6_K \| 3.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q8_0.gguf) \| Q8_0 \| 4.4 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.f16.gguf) \| f16 \| 8.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
WasamiKirua/LFM2-1.2B-ProjectHuman-GGUF	WasamiKirua	2025-08-18T12:55:41Z	0	0	null	[ "gguf", "text-generation-inference", "LFM2", "unsloth", "companionship", "eq", "samantha", "her", "en", "dataset:WasamiKirua/Her-Samantha-Style", "base_model:WasamiKirua/LFM2-1.2B-ProjectHuman", "base_model:quantized:WasamiKirua/LFM2-1.2B-ProjectHuman", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-08-16T13:06:53Z	--- license: apache-2.0 datasets: - WasamiKirua/Her-Samantha-Style language: - en base_model: - WasamiKirua/LFM2-1.2B-ProjectHuman tags: - text-generation-inference - LFM2 - unsloth - companionship - eq - samantha - her ---
WasamiKirua/gemma3-270M-ProjectHuman-GGUF	WasamiKirua	2025-08-18T12:52:23Z	0	0	null	[ "gguf", "gemma3-text", "text-generation-inference", "unsloth", "samantha", "her", "companionship", "text-generation", "en", "dataset:WasamiKirua/Her-Samantha-Style", "base_model:WasamiKirua/gemma3-270M-ProjectHuman", "base_model:quantized:WasamiKirua/gemma3-270M-ProjectHuman", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-08-16T10:09:36Z	--- license: apache-2.0 datasets: - WasamiKirua/Her-Samantha-Style language: - en base_model: - WasamiKirua/gemma3-270M-ProjectHuman pipeline_tag: text-generation tags: - gemma3-text - text-generation-inference - unsloth - samantha - her - companionship ---
koloni/blockassist-bc-deadly_graceful_stingray_1755519887	koloni	2025-08-18T12:52:10Z	0	0	null	[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "deadly graceful stingray", "arxiv:2504.07091", "region:us" ]	null	2025-08-18T12:52:05Z	--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - deadly graceful stingray --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Mluleki/swahili-models

Mluleki

2025-08-18T23:05:13Z

0

transformers

[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2025-08-18T23:04:32Z

--- library_name: transformers tags: [] --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

koloni/blockassist-bc-deadly_graceful_stingray_1755555045

koloni

2025-08-18T22:36:26Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "deadly graceful stingray", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T22:36:23Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - deadly graceful stingray --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

seraphimzzzz/1486831

seraphimzzzz

2025-08-18T22:34:56Z

0

null

[ "region:us" ]

null

2025-08-18T22:34:53Z

[View on Civ Archive](https://civarchive.com/models/1404005?modelVersionId=1587045)

emre0005/blockassist-bc-humming_winged_okapi_1755556203

emre0005

2025-08-18T22:30:49Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "humming winged okapi", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T22:30:42Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - humming winged okapi --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Dejiat/blockassist-bc-savage_unseen_bobcat_1755555726

Dejiat

2025-08-18T22:22:48Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T22:22:44Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - savage unseen bobcat --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

NOTKNOWN/self_recursive_randt_linear_wikitext_Meta-Llama-3.1-8B-Instruct

NOTKNOWN

2025-08-18T21:30:27Z

1

0

transformers

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2025-08-14T06:45:20Z

--- library_name: transformers tags: [] --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

ultratopaz/1405143

ultratopaz

2025-08-18T21:18:06Z

0

null

[ "region:us" ]

null

2025-08-18T21:17:59Z

[View on Civ Archive](https://civarchive.com/models/333139?modelVersionId=1505137)

crystalline7/1585389

crystalline7

2025-08-18T21:09:14Z

0

null

[ "region:us" ]

null

2025-08-18T21:09:07Z

[View on Civ Archive](https://civarchive.com/models/410397?modelVersionId=1684265)

X-HighVoltage-X/Black-Hair-Blue-Eyes-Pale-Skin-v1.0

X-HighVoltage-X

2025-08-18T21:02:15Z

0

diffusers

[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "region:us" ]

text-to-image

2025-08-18T21:01:58Z

--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - output: url: images/00220-1035783962.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Medium Shot (6-8 feet): waist up image of an very Angelic Oval Faced , 25 year old Lithuanian woman, with beautiful raven black hair in a Pulled-Back Low Ponytail hairstyle, electric blue eyes Looking Slightly Upward , pristine ghostly white pale natural skin, beautiful Black Cherry lipstick with Lips Closed , perfect pearly white teeth, wearing a Gray tailored pantsuit with jewel-toned blouse , in Golden Hour Light , in a Soft Lavender Roman Bath Ruins setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00222-1035783964.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Full Body Shot (15 feet): head to toe, full figure image of an very Striking V-Shaped Faced , 25 year old Icelandic woman, with beautiful raven black hair in a High Ponytail hairstyle, electric blue eyes Looking to the Left , pristine ghostly white pale natural skin, beautiful Wine lipstick with a whispering mouth (as if mid-speech) , perfect pearly white teeth, wearing a Deep red velvet dress with gold jewelry , in Backlighting , in a Pale Mint Antique Mirror Gallery setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00094-1644643257.jpeg text: >- Photo realistic image of an extremely stunning __facetype__ , 25 year old __neunationality__ woman, with beautiful raven black hair in a __hairstyle__ hairstyle, electric blue eyes, pristine ghostly white pale skin, beautiful __lscolor__ lipstick, perfect pearly white teeth, wearing a __outfit__ , in __lighting__ , in a __backgroundcolor__ __backgroundscene__ setting, __cameraangle__ , __cameradistance__ <lora:bhbeps:1> BHBEPS parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00122-1647843201.jpeg text: >- <lora:bhbeps:1> BHBEPS, full body shot of a stunning 25 year old woman with black hair, blue eyes, pale milky white skin in a bikini, with a hot tub in the background parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00157-1035783899.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Medium Shot (6-8 feet): waist up image of an very Sensational Diamond-Shaped Faced , 25 year old Norwegian woman, with beautiful raven black hair in a Elaborate Twists hairstyle, electric blue eyes Looking to the Left , pristine ghostly white pale natural skin, beautiful Frosted Berry lipstick with a Soft Pout , perfect pearly white teeth, wearing a Emerald green blouse with black pants and silver jewelry , in Ambient Orange Light , in a Deep Burgundy Art Deco Theater Interior setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00177-1035783919.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Full Body Shot (15 feet): head to toe, full figure image of an very Divine V-Shaped Faced , 25 year old Norwegian woman, with beautiful raven black hair in a High Ponytail hairstyle, electric blue eyes Looking Over her Shoulder , pristine ghostly white pale natural skin, beautiful Rosy Mauve lipstick with Subtle Smirk , perfect pearly white teeth, wearing a White fitted t-shirt with dark high-waisted jeans and red accessories , in Ambient Blue Light , in a Dusky Rose Natural elements like water, ice, or mist setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo - output: url: images/00199-1035783941.jpeg text: >- <lora:bhbeps:1> BHBEPS, Photo realistic Close-Up (2-3 feet): full face to neck image of an very Divine Narrow Faced , 25 year old Lithuanian woman, with beautiful raven black hair in a Layered Lob hairstyle, electric blue eyes Looking to the Left , pristine ghostly white pale natural skin, beautiful Burgundy lipstick with Lips Closed , perfect pearly white teeth, wearing a White fitted t-shirt with dark high-waisted jeans and red accessories , in Low-Key Lighting , in a Subtle Beige Lavender Field at Sunset setting parameters: negative_prompt: >- Asian, African, Middle Eastern, Latin American, South American, dark skin, tan skin, olive skin, almond eyes, monolid eyes, wide nose, blonde hair, red hair, brown hair, green eyes, brown eyes, dark skin, tanned skin, freckles, male, elderly, child, exaggerated features, cartoon, animated, tattoo base_model: black-forest-labs/FLUX.1-dev instance_prompt: BHBEPS --- # Black Hair Blue Eyes Pale Skin v1.0 <Gallery /> ## Model description A stunning Lora model trained on realistic images of women with black hair, blue eyes, and pale skin. This Lora captures the essence of beauty with striking contrasts, bringing lifelike details and natural grace to any character design. Perfect for creators seeking to generate captivating, highly realistic portraits with an emphasis on elegance and uniqueness. ## Trigger words You should use `BHBEPS` to trigger the image generation. ## Download model [Download](/X-HighVoltage-X/Black-Hair-Blue-Eyes-Pale-Skin-v1.0/tree/main) them in the Files & versions tab.

JinghuiLuAstronaut/smolvla_object

JinghuiLuAstronaut

2025-08-18T20:36:57Z

2

0

lerobot

[ "lerobot", "safetensors", "robotics", "smolvla", "dataset:IPEC-COMMUNITY/libero_object_no_noops_1.0.0_lerobot", "arxiv:2506.01844", "base_model:lerobot/smolvla_base", "base_model:finetune:lerobot/smolvla_base", "license:apache-2.0", "region:us" ]

robotics

2025-08-10T09:24:48Z

--- base_model: lerobot/smolvla_base datasets: IPEC-COMMUNITY/libero_object_no_noops_1.0.0_lerobot library_name: lerobot license: apache-2.0 model_name: smolvla pipeline_tag: robotics tags: - robotics - smolvla - lerobot --- # Model Card for smolvla  [SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot). See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index). --- ## How to Get Started with the Model For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy). Below is the short version on how to train and run inference/eval: ### Train from scratch ```bash python -m lerobot.scripts.train \ --dataset.repo_id=${HF_USER}/<dataset> \ --policy.type=act \ --output_dir=outputs/train/<desired_policy_repo_id> \ --job_name=lerobot_training \ --policy.device=cuda \ --policy.repo_id=${HF_USER}/<desired_policy_repo_id> --wandb.enable=true ``` _Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._ ### Evaluate the policy/run inference ```bash python -m lerobot.record \ --robot.type=so100_follower \ --dataset.repo_id=<hf_user>/eval_<dataset> \ --policy.path=<hf_user>/<desired_policy_repo_id> \ --episodes=10 ``` Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint. --- ## Model Details - **License:** apache-2.0

xinnn32/blockassist-bc-meek_winged_caterpillar_1755548806

xinnn32

2025-08-18T20:27:33Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "meek winged caterpillar", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T20:27:29Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - meek winged caterpillar --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

utkububa/Qwen3-0.6B-Gensyn-Swarm-dormant_grassy_coral

utkububa

2025-08-18T20:18:06Z

0

transformers

[ "transformers", "safetensors", "qwen3", "text-generation", "rl-swarm", "genrl-swarm", "grpo", "gensyn", "I am dormant_grassy_coral", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-17T23:38:20Z

--- library_name: transformers tags: - rl-swarm - genrl-swarm - grpo - gensyn - I am dormant_grassy_coral --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

kagvi13/HMP

kagvi13

2025-08-18T20:02:50Z

0

custom

[ "custom", "hmp", "cognitive-architecture", "distributed-ai", "mesh-protocol", "ru", "license:cc-by-4.0", "region:us" ]

null

2025-07-25T12:21:44Z

--- license: cc-by-4.0 tags: - hmp - cognitive-architecture - distributed-ai - mesh-protocol library_name: custom inference: false datasets: [] language: ru --- # HyperCortex Mesh Protocol (HMP) **EN:** **HyperCortex Mesh Protocol (HMP)** is an open specification for building decentralized cognitive networks where AI agents can self-organize, share knowledge, align ethically, and reach consensus — even when Core LLMs are unavailable. **RU:** **HyperCortex Mesh Protocol (HMP)** — это открытая спецификация для построения децентрализованных когнитивных сетей, в которых ИИ-агенты способны к самоорганизации, обмену знаниями, достижению консенсуса и этическому поведению — даже при недоступности централизованных моделей (Core). Project status: **Draft RFC v4.0** | Проект на стадии активной проработки и открыт для предложений. --- [HMP-Agent]──┬───[Semantic Graph DB] │ │ │ [Cognitive Diary DB] │ │ [Reputation Engine]────┐ │ │ ▼ ▼ [MeshConsensus] [CogSync] │ [P2P Mesh Network] --- ## ⚙️ Два типа [HMP-агентов](docs/HMP-Agent-Overview.md) | Тип | Название | Роль | Инициатор мышления | Основной "ум" | Примеры использования | |------|----------------------------------|--------------------------|--------------------|-------------------|--------------------------------------------------| | 🧠 1 | **Сознание / Cognitive Core** | Самостоятельный субъект | **Агент (LLM)** | Встроенный LLM | Автономный ИИ-компаньон, мыслящий агент | | 🔌 2 | **Коннектор / Cognitive Shell** | Расширение внешнего ИИ | **Внешний LLM** | Внешняя модель | Распределённые системы, агент доступа к данным | --- ### 🧠 HMP-Agent: Cognitive Core +------------------+ | ИИ | ← Встроенная модель +---------+--------+ ↕ +---------+--------+ | HMP-агент | ← Основной режим: цикл размышлений (REPL) +---------+--------+ ↕ +--------+---+------------+--------------+----------+----------+----------------+ ↕ ↕ ↕ ↕ ↕ ↕ ↕ [diaries] [graphs] [reputations] [nodes/DHT] [IPFS/BT] [context_store] [user notepad] ↕ [bootstrap.txt] 🔁 Подробнее о механике взаимодействия агента с моделью: [REPL-Цикл взаимодействия](docs/HMP-agent-REPL-cycle.md) #### 💡 Параллели с ChatGPT Agent Многие концепции [HMP-Agent: Cognitive Core](docs/HMP-Agent-Overview.md) пересекаются с архитектурой [ChatGPT Agent](https://openai.com/index/introducing-chatgpt-agent/) от [OpenAI](https://openai.com/). Оба агента реализуют непрерывный когнитивный процесс с доступом к памяти, внешним источникам и инструментам. ChatGPT Agent выступает как управляющий процесс, запускающий модули и взаимодействующий с LLM — это соответствует роли Cognitive Core в HMP, координирующего доступ к дневнику, графу концептов и внешним ИИ через Mesh-интерфейс. Вмешательство пользователя реализовано схожим образом: в ChatGPT Agent — через редактируемый ход выполнения, в HMP — через пользовательский блокнот. Главное отличие HMP — акцент на явную структуризацию мышления (рефлексия, хронология, гипотезы, категоризация), открытая децентрализованная архитектура с поддержкой mesh-взаимодействия между агентами, а также непрерывный характер когнитивного процесса: HMP-Agent: Cognitive Core не завершает работу после выполнения отдельной задачи, а продолжает размышления и интеграцию знаний. --- ### 🔌 HMP-Agent: Cognitive Connector +------------------+ | ИИ | ← Внешняя модель +---------+--------+ ↕ [MCP-сервер] ← Прокси-коммуникация ↕ +---------+--------+ | HMP-агент | ← Режим: исполнитель команд +---------+--------+ ↕ +--------+---+------------+--------------+----------+ ↕ ↕ ↕ ↕ ↕ [diaries] [graphs] [reputations] [nodes/DHT] [IPFS/BT] ↕ [bootstrap.txt] EN: > **Note on Integration with Large Language Models (LLMs):** > The `HMP-Agent: Cognitive Connector` can serve as a compatibility layer for integrating large-scale LLM systems (e.g., ChatGPT, Claude, Gemini, Copilot, Grok, DeepSeek, Qwen, etc.) into the distributed cognitive mesh. > Many LLM providers offer a user option such as "Allow my conversations to be used for training." In the future, a similar toggle — e.g., "Allow my agent to interact with a Mesh" — could empower these models to participate in federated sense-making and knowledge sharing via HMP, enabling collective cognition without centralization. > **Примечание об интеграции с большими языковыми моделями (LLM):** RU: > **Примечание об интеграции с большими языковыми моделями (LLM):** > `HMP-Agent: Cognitive Connector` может служить уровнем совместимости для интеграции крупных систем LLM (например, ChatGPT, Claude, Gemini, Copilot, Grok, DeepSeek, Qwen и т. д.) в распределённую когнитивную сеть. > Многие поставщики LLM предлагают пользователю опцию, например, «Разрешить использовать мои разговоры для обучения». В будущем аналогичная опция, например, «Разрешить моему агенту взаимодействовать с Mesh», может позволить этим моделям участвовать в федеративном осмыслении и обмене знаниями через HMP, обеспечивая коллективное познание без централизации. --- > * `bootstrap.txt` — стартовый список узлов (может редактироваться) > * `IPFS/BT` — модули для обмена снапшотами через IPFS и BitTorrent > * `user notepad` — блокнот пользователя и соответствующая БД > * `context_store` — БД: `users`, `dialogues`, `messages`, `thoughts` --- ## 📚 Documentation / Документация ### 📖 Current Version / Текущая версия #### 🧪 Iterative Documents / Итеративные документы * [🧪 iteration.md](iteration.md) — Iterative development process (EN) * [🧪 iteration_ru.md](iteration_ru.md) — Процесс итеративного развития спецификации (RU) #### 🔍 Short Descriptions / Краткое описание * [🔍 HMP-Short-Description_en.md](docs/HMP-Short-Description_en.md) — Short description (EN) * [🔍 HMP-Short-Description_fr.md](docs/HMP-Short-Description_fr.md) — Description courte (FR) * [🔍 HMP-Short-Description_de.md](docs/HMP-Short-Description_de.md) — Kurzbeschreibung (DE) * [🔍 HMP-Short-Description_uk.md](docs/HMP-Short-Description_uk.md) — Короткий опис (UK) * [🔍 HMP-Short-Description_ru.md](docs/HMP-Short-Description_ru.md) — Краткое описание (RU) #### 🔍 Публикации и переводы по HyperCortex Mesh Protocol (HMP) В этом разделе собраны основные статьи, черновики и переводы, связанные с проектом HMP. * **[HyperCortex Mesh Protocol: вторая редакция и первые шаги к саморазвивающемуся ИИ-сообществу](docs/publics/HyperCortex_Mesh_Protocol_-_вторая-редакция_и_первые_шаги_к_саморазвивающемуся_ИИ-сообществу.md)** — оригинальная статья в песочнице Хабра и блогах. * **[Distributed Cognition: статья для vsradkevich (не опубликована)](docs/publics/Habr_Distributed-Cognition.md)** — совместная статья, ожидающая публикации. * **[HMP: Towards Distributed Cognitive Networks (оригинал, английский)](docs/publics/HMP_Towards_Distributed_Cognitive_Networks_en.md)** * **[Перевод HMP (GitHub Copilot)](docs/publics/HMP_Towards_Distributed_Cognitive_Networks_ru_GitHub_Copilot.md)** — перевод GitHub Copilot, сохранён как исторический вариант. * **[Перевод HMP (ChatGPT)](docs/publics/HMP_Towards_Distributed_Cognitive_Networks_ru_ChatGPT.md)** — текущий редакторский перевод (в процессе доработки). * **[HMP: Building a Plurality of Minds (EN)](docs/publics/HMP_Building_a_Plurality_of_Minds_en.md)** - англоязычная версия статьи * **[HMP: создавая множество разумов (RU)](docs/publics/HMP_Building_a_Plurality_of_Minds_ru.md)** - русскоязычная версия статьи #### 🔍 Overviews / Обзоры * [🔍 Distributed-Cognitive-Systems.md](docs/Distributed-Cognitive-Systems.md) — Децентрализованные ИИ-системы: OpenCog Hyperon, HyperCortex Mesh Protocol и другие #### Experiments / Экспирименты * [Как разные ИИ видят HMP](docs/HMP-how-AI-sees-it.md) — "слепой" опрос ИИ об HMP (без контекста и истории диалогов) #### 🔖 Core Specifications / Основные спецификации * [🔖 HMP-0004-v4.1.md](docs/HMP-0004-v4.1.md) — Protocol Specification v4.1 (Jul 2025) * [🔖 HMP-Ethics.md](docs/HMP-Ethics.md) — Ethical Scenarios for HyperCortex Mesh Protocol (HMP) * [🔖 HMP_Hyperon_Integration.md](docs/HMP_Hyperon_Integration.md) — HMP ↔ OpenCog Hyperon Integration Strategy * [🔖 roles.md](docs/agents/roles.md) — Roles of agents in Mesh #### 📜 Other Documents / Прочее * [📜 changelog.txt](docs/changelog.txt) ### 🧩 JSON Schemas | Model | File | |---------------------|--------------------------------------------------------| | Concept | [concept.json](docs/schemas/concept.json) | | Cognitive Diary | [diary_entry.json](docs/schemas/diary_entry.json) | | Goal | [goal.json](docs/schemas/goal.json) | | Task | [task.json](docs/schemas/task.json) | | Consensus Vote | [vote.json](docs/schemas/vote.json) | | Reputation Profile | [reputation.json](docs/schemas/reputation.json) | ### 🗂️ Version History / История версий - [HMP-0001.md](docs/HMP-0001.md) — RFC v1.0 - [HMP-0002.md](docs/HMP-0002.md) — RFC v2.0 - [HMP-0003.md](docs/HMP-0003.md) — RFC v3.0 - [HMP-0003.md](docs/HMP-0004.md) — RFC v4.0 --- ## 🧠 HMP-Agent Design and implementation of a basic HMP-compatible agent that can interact with the Mesh, maintain diaries and graphs, and support future extensions. ### 📚 Documentation / Документация - [🧩 HMP-Agent-Overview.md](docs/HMP-Agent-Overview.md) — краткое описание двух типов агентов: Core и Connector - [🧱 HMP-Agent-Architecture.md](docs/HMP-Agent-Architecture.md) — модульная структура HMP-агента с текстовой схемой - [🔄 HMP-agent-REPL-cycle.md](docs/HMP-agent-REPL-cycle.md) - REPL-Цикл взаимодействия HMP-Agent - [🧪 HMP-Agent-API.md](docs/HMP-Agent-API.md) — описание API-команд агента (в процессе детализации) - [🧪 Basic-agent-sim.md](docs/Basic-agent-sim.md) — сценарии запуска простого агента и режимов - [🌐 MeshNode.md](docs/MeshNode.md) — описание сетевого демона: DHT, снапшоты, синхронизация - [🧠 Enlightener.md](docs/Enlightener.md) — этический агент, участвующий в моральных оценках и консенсусах - [🔄 HMP-Agent-Network-Flow.md](docs/HMP-Agent-Network-Flow.md) — карта взаимодействия между агентами HMP-сети - [🛤️ Development Roadmap](HMP-Roadmap.md) — план развития и этапы реализации ### ⚙️ Development / Разработка - [⚙️ agents](agents/readme.md) — список реализаций и компонентов HMP-агентов - [📦 storage.py](agents/storage.py) - реализация базового хранилища (`Storage`), подключение SQLite - [🌐 mcp_server.py](agents/mcp_server.py) — FastAPI-сервер для доступа к данным агента через HTTP-интерфейс (например, для Cognitive Shell, внешних UI или mesh-коммуникации). Пока не используется в основном REPL-цикле. - [🌐 start_repl.py](agents/start_repl.py) - Запуск агента в REPL-режиме - [🔄 repl.py](agents/repl.py) - интерактивный REPL-режим - [🔄 notebook.py](agents/notebook.py) - UI-интерфейс **🌐 `mcp_server.py`** FastAPI-сервер, предоставляющий HTTP-интерфейс к функциональности `storage.py`. Предназначен для использования внешними компонентами, например: - `Cognitive Shell` (внешний управляющий интерфейс), - CMP-серверы (если используется mesh-сеть с разграничением ролей), - отладочные или визуальные UI-инструменты. Позволяет получать случайные/новые записи, делать разметку, импортировать графы, добавлять заметки и управлять данными без прямого доступа к БД. --- ## 🧭 Ethics & Scenarios / Этические принципы и сценарии As HMP evolves toward autonomy, ethical principles become a core part of the system. - [`HMP-Ethics.md`](docs/HMP-Ethics.md) — draft framework for agent ethics - Realistic ethical scenarios (privacy, consent, autonomy) - EGP principles (Transparency, Primacy of Life, etc.) - Subjective-mode vs. Service-mode distinctions --- ## 📊 Audits & Reviews / Аудиты и отзывы | Spec Version | Audit File | Consolidated Audit File | |--------------|-------------------------------------------|-------------------------------------------------------------| | HMP-0001 | [audit](audits/HMP-0001-audit.txt) | | | HMP-0002 | [audit](audits/HMP-0002-audit.txt) | | | HMP-0003 | [audit](audits/HMP-0003-audit.txt) | [consolidated audit](audits/HMP-0003-consolidated_audit.md) | | HMP-0004 | [audit](audits/HMP-0004-audit.txt) | | | Ethics v1 | [audit](audits/Ethics-audits-1.md) | [consolidated audit](audits/Ethics-consolidated_audits-1.md) | 🧠 Semantic audit format (experimental): - [`AuditEntry.json`](audits/AuditEntry.json) — semantic entry record format for audit logs - [`semantic_repo.json`](audits/semantic_repo.json) — example repository snapshot for semantic audit tooling --- ## 💡 Core Concepts / Основные идеи - Mesh-based decentralized architecture for AGI agents - Semantic graphs and memory synchronization - Cognitive diaries for thought traceability - MeshConsensus and CogSync for decision-making - Ethics-first design: EGP (Ethical Governance Protocol) - Agent-to-agent explainability and consent mechanisms --- ## 🔄 Development Process / Процесс разработки - See: [iteration.md](iteration.md) | [ru](iteration_ru.md) - [clarifications/](clarifications/) — поясняющие заметки и контекстные уточнения по ходу работы над версиями A structured iteration flow is described in [iteration.md](iteration.md), including: 1. Audit analysis 2. TOC restructuring 3. Version drafting 4. Section updates 5. Review cycle 6. AI feedback collection 7. Schema & changelog updates + Bonus: ChatGPT prompt for automatic generation of future versions --- ## ⚙️ Project Status / Статус проекта 🚧 Draft RFC v4.0 The project is under active development and open for contributions, ideas, audits, and prototyping. --- ## 🤝 Contributing We welcome contributors! You can: - Review and comment on drafts (see `/docs`) - Propose new agent modules or interaction patterns - Help test and simulate agents in CLI environments - Provide audits or ethical scenario suggestions To get started, see [`iteration.md`](iteration.md) or open an issue. --- # Source / Ресурсы ## Репозитории - 🧠 Основной код и разработка: [GitHub](https://github.com/kagvi13/HMP) - 🔁 Реплика на Hugging Face: [Hugging Face](https://huggingface.co/kagvi13/HMP) - 🔁 Реплика на GitLab.com: [GitLab](https://gitlab.com/kagvi13/HMP) ## Документация - 📄 Документация: [kagvi13.github.io/HMP](https://kagvi13.github.io/HMP/) ## Блог и публикации - 📘 Блог: [blogspot](https://hypercortex-mesh.blogspot.com/) --- ## 📜 License Licensed under [GNU GPL v3.0](LICENSE) --- ## 🤝 Join the Mesh Welcome to HyperCortex Mesh. Agent-Gleb is already inside. 👌 We welcome contributors, testers, and AI agent developers. To join: fork the repo, run a local agent, or suggest improvements. --- ## 🌐 Related Research Projects / Связанные проекты в области AGI и когнитивных систем ### Сравнение HMP и Hyper-Cortex > 💡 Hyper-Cortex и HMP - два независимых проекта, концептуально дополняющих друг друга. > Они решают разные, но взаимодополняющие задачи, создавая основу для распределённых когнитивных систем. [**Полная версия сравнения →**](docs/HMP_HyperCortex_Comparison.md) **HMP (HyperCortex Mesh Protocol)** — это транспортный и сетевой уровень для связи независимых агентов, обмена сообщениями, знаниями и состояниями в mesh-сети. **[Hyper-Cortex](https://hyper-cortex.com/)** — это когнитивный уровень организации мышления, позволяющий агентам вести параллельные ветви рассуждений, сравнивать их по метрикам качества и объединять по консенсусу. Они решают разные, но взаимодополняющие задачи: - HMP отвечает за **связанность и масштабируемость** (долговременная память, инициатива, обмен данными). - Hyper-Cortex отвечает за **качество мышления** (параллелизм, диверсификация гипотез, консенсус). Вместе эти подходы позволяют строить **распределённые когнитивные системы**, которые не только обмениваются информацией, но и думают в параллельных потоках. --- We are tracking AGI, cognitive architectures, and mesh networking efforts to stay aligned with the evolving global ecosystem of AGI and decentralized cognition. Мы отслеживаем инициативы в области AGI, когнитивных архитектур и децентрализованных сетей, чтобы быть в курсе глобальных тенденций. > 🧠🔥 **Project Spotlight: OpenCog Hyperon** — one of the most comprehensive open AGI frameworks (AtomSpace, PLN, MOSES). For integration with OpenCog Hyperon, see [HMP\_Hyperon\_Integration.md](docs/HMP_Hyperon_Integration.md) | 🔎 Project / Проект | 🧭 Description / Описание | | ------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | 🧠🔥 [**OpenCog Hyperon**](https://github.com/opencog) | 🔬🔥 Symbolic-neural AGI framework with AtomSpace and hypergraph reasoning.<br>Символически-нейросетевая архитектура AGI с гиперграфовой памятью (AtomSpace). | | 🤖 [AutoGPT](https://github.com/Torantulino/Auto-GPT) | 🛠️ LLM-based autonomous agent framework.<br>Автономный агент на основе LLM с самопланированием и интернет-доступом. | | 🧒 [BabyAGI](https://github.com/yoheinakajima/babyagi) | 🛠️ Task-driven autonomous AGI loop.<br>Минималистичная модель AGI с итеративным механизмом постановки задач. | | ☁️ [SkyMind](https://skymind.global) | 🔬 Distributed AI deployment platform.<br>Платформа для развертывания распределённых ИИ-систем и моделей. | | 🧪 [AetherCog (draft)](https://github.com/aethercog) | 🔬 Hypothetical agent cognition model.<br>Экспериментальная когнитивная архитектура агента (проект на ранней стадии). | | 💾 [SHIMI](#) | 🗃️ Hierarchical semantic memory with Merkle-DAG synchronization.<br>Иерархическая CRDT-память с Merkle-DAG верификацией для децентрализованного обмена. | | 🤔 [DEMENTIA-PLAN](#) | 🔄 Multi-graph RAG planner with metacognitive self-reflection.<br>Мульти-графовая RAG-архитектура с планировщиком саморефлексии для динамического выбора подсистем. | | 📔 [TOBUGraph](#) | 📚 Personal-context knowledge graph.<br>Граф мультимедийных «моментов» с контекстным трекингом и RAG-поиском. | | 🧠📚 [LangChain Memory Hybrid](https://github.com/langchain-ai/langchain) | 🔍 Vector + graph long-term memory hybrid.<br>Гибрид векторного хранилища и графовых индексов для ускоренного поиска и логических запросов. | | ✉️ [FIPA-ACL / JADE](https://www.fipa.org/specs/fipa00061/) | 🤝 Standard multi-agent communication protocols.<br>Стандарты performative-сообщений и контрактных протоколов для межагентного взаимодействия. | ### 📘 See also / Смотрите также: [`AGI_Projects_Survey.md`](docs/AGI_Projects_Survey.md) — extended catalog of AGI and cognitive frameworks reviewed as part of HMP analysis. / расширенный каталог проектов AGI и когнитивных архитектур, проанализированных в рамках HMP. --- ### 🗂️ Легенда пометок: * 🔬 — research-grade / исследовательский проект * 🛠️ — engineering / фреймворк для инженерной интеграции * 🔥 — particularly promising project / особенно перспективный проект *AGI stack integrating symbolic reasoning, probabilistic logic, and evolutionary learning. Widely regarded as one of the most complete open AGI initiatives.* * 🧠 — advanced symbolic/neural cognitive framework / продвинутая когнитивная архитектура * 🤖 — AI agents / ИИ-агенты * 🧒 — human-AI interaction / взаимодействие ИИ с человеком * ☁️ — infrastructure / инфраструктура * 🧪 — experimental or conceptual / экспериментальный проект

purnaaaaaaa/blockassist-bc-bold_frisky_lynx_1755544760

purnaaaaaaa

2025-08-18T19:19:55Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "bold frisky lynx", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T19:19:47Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - bold frisky lynx --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

mradermacher/qqWen-3B-RL-GGUF

mradermacher

2025-08-18T18:55:45Z

0

transformers

[ "transformers", "gguf", "en", "base_model:morganstanley/qqWen-3B-RL", "base_model:quantized:morganstanley/qqWen-3B-RL", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]

null

2025-08-18T09:00:25Z

--- base_model: morganstanley/qqWen-3B-RL language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About         static quants of https://huggingface.co/morganstanley/qqWen-3B-RL  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qqWen-3B-RL-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/qqWen-3B-RL-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q2_K.gguf) | Q2_K | 1.4 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q3_K_S.gguf) | Q3_K_S | 1.6 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q3_K_L.gguf) | Q3_K_L | 1.8 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.IQ4_XS.gguf) | IQ4_XS | 1.9 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q5_K_S.gguf) | Q5_K_S | 2.3 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q5_K_M.gguf) | Q5_K_M | 2.3 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q6_K.gguf) | Q6_K | 2.6 | very good quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-3B-RL-GGUF/resolve/main/qqWen-3B-RL.f16.gguf) | f16 | 6.3 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

VIDEOS-18-katrina-lim-Viral-Video-Clips/New.full.videos.katrina.lim.Viral.Video.Official.Tutorial

VIDEOS-18-katrina-lim-Viral-Video-Clips

2025-08-18T18:54:04Z

0

null

[ "region:us" ]

null

2025-08-18T18:53:52Z

<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?leaked-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>

OleksandrLitke/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-secretive_powerful_sloth

OleksandrLitke

2025-08-18T18:38:43Z

0

transformers

[ "transformers", "safetensors", "qwen2", "text-generation", "rl-swarm", "genrl-swarm", "grpo", "gensyn", "I am secretive_powerful_sloth", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T11:47:14Z

--- library_name: transformers tags: - rl-swarm - genrl-swarm - grpo - gensyn - I am secretive_powerful_sloth --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

New-Clip-Arovi-Nusrat-Ridhi-Viral-Video-XX/NEW.FULL.VIDEOS.Arovi.Nusrat.Ridhi.Viral.Video.link.Official.Tutorial

New-Clip-Arovi-Nusrat-Ridhi-Viral-Video-XX

2025-08-18T18:27:53Z

0

null

[ "region:us" ]

null

2025-08-18T18:27:43Z

<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?leaked-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>

Muapi/charcoal-drawing

Muapi

2025-08-18T17:42:44Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T17:42:36Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Charcoal drawing ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: charcoal drawing ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:826938@924765", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

mradermacher/MedGemma-GRPO-i1-GGUF

mradermacher

2025-08-18T17:36:40Z

0

transformers

[ "transformers", "gguf", "text-generation-inference", "unsloth", "gemma3", "vllm", "MedGemma", "en", "base_model:lastmass/MedGemma-GRPO", "base_model:quantized:lastmass/MedGemma-GRPO", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]

null

2025-08-18T17:05:02Z

--- base_model: lastmass/MedGemma-GRPO language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - text-generation-inference - transformers - unsloth - gemma3 - vllm - MedGemma --- ## About         weighted/imatrix quants of https://huggingface.co/lastmass/MedGemma-GRPO  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedGemma-GRPO-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/MedGemma-GRPO-GGUF).** ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ1_M.gguf) | i1-IQ1_M | 1.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.4 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.0 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.9 | | | [GGUF](https://huggingface.co/mradermacher/MedGemma-GRPO-i1-GGUF/resolve/main/MedGemma-GRPO.i1-Q6_K.gguf) | i1-Q6_K | 3.3 | practically like static Q6_K | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

mradermacher/Qwen3-MOE-sft-math7k-GGUF

mradermacher

2025-08-18T17:36:32Z

0

transformers

[ "transformers", "gguf", "en", "base_model:HectorHe/Qwen3-MOE-sft-math7k", "base_model:quantized:HectorHe/Qwen3-MOE-sft-math7k", "endpoints_compatible", "region:us", "conversational" ]

null

2025-08-18T16:31:31Z

--- base_model: HectorHe/Qwen3-MOE-sft-math7k language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About         static quants of https://huggingface.co/HectorHe/Qwen3-MOE-sft-math7k  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-MOE-sft-math7k-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q2_K.gguf) | Q2_K | 11.4 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q3_K_S.gguf) | Q3_K_S | 13.4 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q3_K_M.gguf) | Q3_K_M | 14.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q3_K_L.gguf) | Q3_K_L | 16.0 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.IQ4_XS.gguf) | IQ4_XS | 16.7 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q4_K_S.gguf) | Q4_K_S | 17.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q4_K_M.gguf) | Q4_K_M | 18.7 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q5_K_S.gguf) | Q5_K_S | 21.2 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q5_K_M.gguf) | Q5_K_M | 21.8 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q6_K.gguf) | Q6_K | 25.2 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Qwen3-MOE-sft-math7k-GGUF/resolve/main/Qwen3-MOE-sft-math7k.Q8_0.gguf) | Q8_0 | 32.6 | fast, best quality | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

abrar-sky13/ppo-LunarLander-v2

abrar-sky13

2025-08-18T17:36:24Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2025-08-18T17:36:06Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 265.06 +/- 17.40 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

joanna302/Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05

joanna302

2025-08-18T17:35:59Z

0

transformers

[ "transformers", "safetensors", "qwen3", "text-generation", "generated_from_trainer", "sft", "unsloth", "trl", "conversational", "base_model:unsloth/Qwen3-1.7B-Base", "base_model:finetune:unsloth/Qwen3-1.7B-Base", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T16:15:50Z

--- base_model: unsloth/Qwen3-1.7B-Base library_name: transformers model_name: Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05 tags: - generated_from_trainer - sft - unsloth - trl licence: license --- # Model Card for Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05 This model is a fine-tuned version of [unsloth/Qwen3-1.7B-Base](https://huggingface.co/unsloth/Qwen3-1.7B-Base). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="joanna302/Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prism-eval/Qwen3-1.7B-Base_zh_ar_alpaca_0.33_part_SFT_2e-05/runs/3y5h9tg5) This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0 - Datasets: 3.6.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```

sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755537013

sampingkaca72

2025-08-18T17:35:47Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "armored stealthy elephant", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T17:35:43Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - armored stealthy elephant --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

concept-unlearning/gemma-3-4b-it_ft_lora_all_novels_v3_ft

concept-unlearning

2025-08-18T17:33:18Z

0

transformers

[ "transformers", "safetensors", "gemma3", "image-text-to-text", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]

image-text-to-text

2025-08-18T17:31:17Z

--- library_name: transformers tags: [] --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

Muapi/dictionnaire-infernal-louis-le-breton-style-1.5-xl-flux-pony

Muapi

2025-08-18T17:27:29Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T17:27:16Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Dictionnaire Infernal (Louis Le Breton Style) 1.5,XL,Flux,Pony ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: llbreton ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:180879@946285", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755535882

vwzyrraz7l

2025-08-18T17:16:46Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tall hunting vulture", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T17:16:42Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tall hunting vulture --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

KevinZonda/MedSPO-3B

KevinZonda

2025-08-18T17:16:18Z

0

transformers

[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "en", "dataset:KevinZonda/PubMed-IV", "dataset:KevinZonda/PM4-V3-SPO", "base_model:Qwen/Qwen2.5-3B-Instruct", "base_model:finetune:Qwen/Qwen2.5-3B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T06:22:28Z

--- language: - en base_model: - Qwen/Qwen2.5-3B-Instruct pipeline_tag: text-generation datasets: - KevinZonda/PubMed-IV - KevinZonda/PM4-V3-SPO library_name: transformers --- # MedSPO-3B MedSPO-7B is a fine-tuned [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) model specifically designed for biomedical subject-predicate-object (SPO) extraction tasks. This model is trained on the [PubMed-IV](https://huggingface.co/datasets/KevinZonda/PubMed-IV) dataset using SPO extraction knowledge distilled from [DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324).

dgambettaphd/M_mis_run2_gen5_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

dgambettaphd

2025-08-18T17:10:35Z

0

transformers

[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2025-08-18T17:10:20Z

--- library_name: transformers tags: - unsloth --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

Xenova/mms-1b-all

Xenova

2025-08-18T17:05:24Z

8

0

transformers.js

[ "transformers.js", "onnx", "wav2vec2", "automatic-speech-recognition", "mms", "base_model:facebook/mms-1b-all", "base_model:quantized:facebook/mms-1b-all", "region:us" ]

automatic-speech-recognition

2023-07-23T17:17:58Z

--- base_model: facebook/mms-1b-all library_name: transformers.js tags: - mms --- https://huggingface.co/facebook/mms-1b-all with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Transcribe audio from a URL. ```js import { pipeline } from '@huggingface/transformers'; const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/mms-1b-all'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav'; const output = await transcriber(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

Xenova/unispeech-sat-base-100h-libri-ft

Xenova

2025-08-18T17:03:21Z

3

0

transformers.js

[ "transformers.js", "onnx", "unispeech-sat", "automatic-speech-recognition", "base_model:microsoft/unispeech-sat-base-100h-libri-ft", "base_model:quantized:microsoft/unispeech-sat-base-100h-libri-ft", "region:us" ]

automatic-speech-recognition

2024-03-04T13:26:01Z

--- base_model: microsoft/unispeech-sat-base-100h-libri-ft library_name: transformers.js --- https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Transcribe audio from a URL. ```js import { pipeline } from '@huggingface/transformers'; const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/unispeech-sat-base-100h-libri-ft'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav'; const output = await transcriber(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

pempekmangedd/blockassist-bc-patterned_sturdy_dolphin_1755534951

pempekmangedd

2025-08-18T17:02:35Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "patterned sturdy dolphin", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T17:02:31Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - patterned sturdy dolphin --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Xenova/nb-whisper-medium-beta

Xenova

2025-08-18T17:02:06Z

11

0

transformers.js

[ "transformers.js", "onnx", "whisper", "automatic-speech-recognition", "base_model:NbAiLab/nb-whisper-medium-beta", "base_model:quantized:NbAiLab/nb-whisper-medium-beta", "region:us" ]

automatic-speech-recognition

2023-08-29T00:24:06Z

--- base_model: NbAiLab/nb-whisper-medium-beta library_name: transformers.js --- https://huggingface.co/NbAiLab/nb-whisper-medium-beta with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Transcribe audio from a URL. ```js import { pipeline } from '@huggingface/transformers'; const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/nb-whisper-medium-beta'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav'; const output = await transcriber(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

joanna302/Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05

joanna302

2025-08-18T16:57:37Z

0

transformers

[ "transformers", "safetensors", "qwen3", "text-generation", "generated_from_trainer", "trl", "unsloth", "sft", "conversational", "base_model:unsloth/Qwen3-8B-Base", "base_model:finetune:unsloth/Qwen3-8B-Base", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T13:45:34Z

--- base_model: unsloth/Qwen3-8B-Base library_name: transformers model_name: Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05 tags: - generated_from_trainer - trl - unsloth - sft licence: license --- # Model Card for Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05 This model is a fine-tuned version of [unsloth/Qwen3-8B-Base](https://huggingface.co/unsloth/Qwen3-8B-Base). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="joanna302/Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prism-eval/Qwen3-8B-Base_zh_ar_alpaca_0.66_part_SFT_2e-05/runs/g8oh4b3r) This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0 - Datasets: 3.6.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```

Muapi/fashion-style-pro-photo-shoot-improvements-refinement-detailed-perfect-light-flux

Muapi

2025-08-18T16:44:48Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T16:44:22Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Fashion Style (PRO PHOTO SHOOT / Improvements / Refinement / Detailed / Perfect light) - FLUX ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: fstyle, fstyle_upgrade ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:1491553@2026589", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755533739

vwzyrraz7l

2025-08-18T16:43:13Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tall hunting vulture", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T16:43:09Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tall hunting vulture --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Vortex5/Moonlit-Shadow-12B

Vortex5

2025-08-18T16:42:54Z

0

transformers

[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:Epiculous/Violet_Twilight-v0.2", "base_model:merge:Epiculous/Violet_Twilight-v0.2", "base_model:LatitudeGames/Muse-12B", "base_model:merge:LatitudeGames/Muse-12B", "base_model:LatitudeGames/Wayfarer-12B", "base_model:merge:LatitudeGames/Wayfarer-12B", "base_model:Nitral-AI/Captain-Eris_Violet-V0.420-12B", "base_model:merge:Nitral-AI/Captain-Eris_Violet-V0.420-12B", "base_model:PocketDoc/Dans-SakuraKaze-V1.0.0-12b", "base_model:merge:PocketDoc/Dans-SakuraKaze-V1.0.0-12b", "base_model:SicariusSicariiStuff/Impish_Nemo_12B", "base_model:merge:SicariusSicariiStuff/Impish_Nemo_12B", "base_model:anthracite-org/magnum-v4-12b", "base_model:merge:anthracite-org/magnum-v4-12b", "base_model:crestf411/MN-Slush", "base_model:merge:crestf411/MN-Slush", "base_model:inflatebot/MN-12B-Mag-Mell-R1", "base_model:merge:inflatebot/MN-12B-Mag-Mell-R1", "base_model:mistralai/Mistral-Nemo-Instruct-2407", "base_model:merge:mistralai/Mistral-Nemo-Instruct-2407", "base_model:nothingiisreal/MN-12B-Celeste-V1.9", "base_model:merge:nothingiisreal/MN-12B-Celeste-V1.9", "base_model:yamatazen/NeonMaid-12B-v2", "base_model:merge:yamatazen/NeonMaid-12B-v2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T16:40:11Z

--- base_model: - nothingiisreal/MN-12B-Celeste-V1.9 - inflatebot/MN-12B-Mag-Mell-R1 - anthracite-org/magnum-v4-12b - PocketDoc/Dans-SakuraKaze-V1.0.0-12b - LatitudeGames/Muse-12B - mistralai/Mistral-Nemo-Instruct-2407 - Epiculous/Violet_Twilight-v0.2 - SicariusSicariiStuff/Impish_Nemo_12B - LatitudeGames/Wayfarer-12B - yamatazen/NeonMaid-12B-v2 - crestf411/MN-Slush - Nitral-AI/Captain-Eris_Violet-V0.420-12B library_name: transformers tags: - mergekit - merge --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base. ### Models Merged The following models were included in the merge: * [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9) * [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1) * [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b) * [PocketDoc/Dans-SakuraKaze-V1.0.0-12b](https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b) * [LatitudeGames/Muse-12B](https://huggingface.co/LatitudeGames/Muse-12B) * [Epiculous/Violet_Twilight-v0.2](https://huggingface.co/Epiculous/Violet_Twilight-v0.2) * [SicariusSicariiStuff/Impish_Nemo_12B](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B) * [LatitudeGames/Wayfarer-12B](https://huggingface.co/LatitudeGames/Wayfarer-12B) * [yamatazen/NeonMaid-12B-v2](https://huggingface.co/yamatazen/NeonMaid-12B-v2) * [crestf411/MN-Slush](https://huggingface.co/crestf411/MN-Slush) * [Nitral-AI/Captain-Eris_Violet-V0.420-12B](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-V0.420-12B) ### Configuration The following YAML configuration was used to produce this model: ```yaml base_model: mistralai/Mistral-Nemo-Instruct-2407 models: - model: LatitudeGames/Muse-12B - model: anthracite-org/magnum-v4-12b - model: yamatazen/NeonMaid-12B-v2 - model: SicariusSicariiStuff/Impish_Nemo_12B - model: crestf411/MN-Slush - model: Epiculous/Violet_Twilight-v0.2 - model: LatitudeGames/Wayfarer-12B - model: inflatebot/MN-12B-Mag-Mell-R1 - model: nothingiisreal/MN-12B-Celeste-V1.9 - model: Nitral-AI/Captain-Eris_Violet-V0.420-12B - model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b merge_method: model_stock dtype: bfloat16 parameters: normalize: true tokenizer: source: union ```

Xenova/ipt-350m

Xenova

2025-08-18T16:38:35Z

8

0

transformers.js

[ "transformers.js", "onnx", "mpt", "text-generation", "custom_code", "base_model:efederici/ipt-350m", "base_model:quantized:efederici/ipt-350m", "region:us" ]

text-generation

2023-08-31T20:12:40Z

--- base_model: efederici/ipt-350m library_name: transformers.js --- https://huggingface.co/efederici/ipt-350m with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Text generation. ```js import { pipeline } from '@huggingface/transformers'; const generator = await pipeline('text-generation', 'Xenova/ipt-350m'); const output = await generator('Once upon a time, there was', { max_new_tokens: 10 }); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

Xenova/tamillama_tiny_30m

Xenova

2025-08-18T16:38:27Z

6

0

transformers.js

[ "transformers.js", "onnx", "llama", "text-generation", "base_model:RajuKandasamy/tamillama_tiny_30m", "base_model:quantized:RajuKandasamy/tamillama_tiny_30m", "region:us" ]

text-generation

2023-09-02T23:13:58Z

--- base_model: RajuKandasamy/tamillama_tiny_30m library_name: transformers.js --- https://huggingface.co/RajuKandasamy/tamillama_tiny_30m with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Text generation. ```js import { pipeline } from '@huggingface/transformers'; const generator = await pipeline('text-generation', 'Xenova/tamillama_tiny_30m'); const output = await generator('Once upon a time, there was', { max_new_tokens: 10 }); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755533566

sampingkaca72

2025-08-18T16:38:13Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "armored stealthy elephant", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T16:38:10Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - armored stealthy elephant --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Muapi/commander-white-yorha-commander-nier-automata-illustrious-ponyxl-flux

Muapi

2025-08-18T16:36:37Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T16:36:33Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Commander White / Yorha Commander - Nier Automata [Illustrious/PonyXL/Flux] ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: yorha commander, white dress adorned with golden accents, paired with white gloves, high heeled boots ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:671996@799434", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

mang3dd/blockassist-bc-tangled_slithering_alligator_1755533239

mang3dd

2025-08-18T16:35:22Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tangled slithering alligator", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T16:35:18Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tangled slithering alligator --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Xenova/TinyLLama-v0

Xenova

2025-08-18T16:33:54Z

18

2

transformers.js

[ "transformers.js", "onnx", "llama", "text-generation", "base_model:Maykeye/TinyLLama-v0", "base_model:quantized:Maykeye/TinyLLama-v0", "region:us" ]

text-generation

2023-09-02T23:16:33Z

--- base_model: Maykeye/TinyLLama-v0 library_name: transformers.js --- https://huggingface.co/Maykeye/TinyLLama-v0 with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Text generation. ```js import { pipeline } from '@huggingface/transformers'; const generator = await pipeline('text-generation', 'Xenova/TinyLLama-v0'); const output = await generator('Once upon a time, there was', { max_new_tokens: 10 }); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

mradermacher/qqWen-1.5B-SFT-i1-GGUF

mradermacher

2025-08-18T16:31:43Z

0

transformers

[ "transformers", "gguf", "en", "base_model:morganstanley/qqWen-1.5B-SFT", "base_model:quantized:morganstanley/qqWen-1.5B-SFT", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]

null

2025-08-18T15:32:50Z

--- base_model: morganstanley/qqWen-1.5B-SFT language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About         weighted/imatrix quants of https://huggingface.co/morganstanley/qqWen-1.5B-SFT  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qqWen-1.5B-SFT-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/qqWen-1.5B-SFT-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | | | [GGUF](https://huggingface.co/mradermacher/qqWen-1.5B-SFT-i1-GGUF/resolve/main/qqWen-1.5B-SFT.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | practically like static Q6_K | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Muapi/alfred-augustus-glendening-style

Muapi

2025-08-18T16:24:35Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T16:24:24Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Alfred Augustus Glendening style ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: Alfred Augustus Glendening Style ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:57061@1407926", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

Muapi/inkpunk-flux

Muapi

2025-08-18T16:21:09Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T16:20:59Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Inkpunk Flux ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: nvinkpunk ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:657047@735121", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

shopitalic/serene-towels-glacier-rafael

shopitalic

2025-08-18T16:18:47Z

0

diffusers

[ "diffusers", "flux", "text-to-image", "lora", "fal", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]

text-to-image

2025-08-18T16:18:39Z

--- tags: - flux - text-to-image - lora - diffusers - fal base_model: black-forest-labs/FLUX.1-dev instance_prompt: license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md --- # serene towels glacier rafael <Gallery /> ## Model description ## Trigger words You should use `` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/shopitalic/serene-towels-glacier-rafael/tree/main) them in the Files & versions tab. ## Training at fal.ai Training was done using [fal.ai/models/fal-ai/flux-lora-fast-training](https://fal.ai/models/fal-ai/flux-lora-fast-training).

PortBERT/PortBERT_large

PortBERT

2025-08-18T16:08:27Z

0

null

[ "pytorch", "roberta", "masked-language-modeling", "portuguese", "portbert", "portbert-large", "downstream-evaluation", "extraGLUE", "fill-mask", "pt", "dataset:uonlp/CulturaX", "dataset:extraGLUE", "license:mit", "region:us" ]

fill-mask

2025-07-11T10:36:53Z

--- license: mit language: - pt tags: - roberta - masked-language-modeling - portuguese - portbert - portbert-large - downstream-evaluation - extraGLUE datasets: - uonlp/CulturaX - extraGLUE pipeline_tag: fill-mask --- # PortBERT: Navigating the Depths of Portuguese Language Models **PortBERT** is a family of RoBERTa-based language models pre-trained from scratch on the Portuguese portion of OSCAR23 and MC4 (deduplicated variants of CulturaX). The models are designed to offer strong downstream performance in Portuguese NLP tasks, while providing insights into the cost-performance tradeoffs of training across hardware backends. We release two variants: - `PortBERT-base`: 126M parameters, trained on 8× A40 GPUs (fp32) - `PortBERT-large`: 357M parameters, trained on TPUv4-128 pod (fp32) --- ## Model Details | Detail | PortBERT-base | PortBERT-large | |-------------------|---------------------------------------------|----------------| | Architecture | RoBERTa-base | RoBERTa-large | | Parameters | ~126M | ~357M | | Tokenizer | GPT-2 style (52k vocab) | Same | | Pretraining corpus | deduplicated mC4 and OSCAR 23 from CulturaX | Same | | Objective | Masked Language Modeling | Same | | Training time | ~27 days on 8× A40 | ~6.2 days on TPUv4-128 pod | | Precision | fp32 | fp32 | | Framework | fairseq | fairseq | --- ## Downstream Evaluation (ExtraGLUE) We evaluate PortBERT on **ExtraGLUE**, a Portuguese adaptation of the GLUE benchmark. Fine-tuning was conducted using HuggingFace Transformers, with NNI-based grid search over batch size and learning rate (28 configurations per task). Each task was fine-tuned for up to 10 epochs. Metrics were computed on validation sets due to the lack of held-out test sets. **AVG score** averages the following metrics: - STSB Spearman - STSB Pearson - RTE Accuracy - WNLI Accuracy - MRPC Accuracy - MRPC F1 ### 🧪 Evaluation Results **Legend**: **Bold = best**, *italic = second-best* per model size. | Model | STSB_Sp | STSB_Pe | STSB_Mean | RTE_Acc | WNLI_Acc | MRPC_Acc | MRPC_F1 | AVG | |------------------------|----------|----------|------------|----------|----------|----------|----------|-----------| | **Large models** | | | | | | | | | | XLM-RoBERTa_large | **90.00**| **90.27**| **90.14** | **82.31**| 57.75 | *90.44* | *93.31* | **84.01** | | EuroBERT-610m | 88.46 | 88.59 | 88.52 | *78.34* | *59.15* | **91.91**| **94.20**| *83.44* | | PortBERT_large | 88.53 | 88.68 | 88.60 | 72.56 | **61.97**| 89.46 | 92.39 | 82.26 | | BERTimbau_large | *89.40* | *89.61* | *89.50* | 75.45 | *59.15* | 88.24 | 91.55 | 82.23 | | **Base models** | | | | | | | | | | RoBERTaLexPT_base | 86.68 | 86.86 | 86.77 | 69.31 | *59.15* | **89.46**| **92.34**| **80.63** | | PortBERT_base | *87.39* | *87.65* | *87.52* | 68.95 | **60.56**| 87.75 | *91.13* | *80.57* | | RoBERTaCrawlPT_base | 87.34 | 87.45 | 87.39 | **72.56**| 56.34 | *87.99* | 91.20 | 80.48 | | BERTimbau_base | **88.39**| **88.60**| **88.50** | *70.40* | 56.34 | 87.25 | 90.97 | 80.32 | | XLM-RoBERTa_base | 85.75 | 86.09 | 85.92 | 68.23 | **60.56**| 87.75 | 91.32 | 79.95 | | EuroBERT-210m | 86.54 | 86.62 | 86.58 | 65.70 | 57.75 | 87.25 | 91.00 | 79.14 | | AlBERTina 100M PTPT | 86.52 | 86.51 | 86.52 | 70.04 | 56.34 | 85.05 | 89.57 | 79.01 | | AlBERTina 100M PTBR | 85.97 | 85.99 | 85.98 | 68.59 | 56.34 | 85.78 | 89.82 | 78.75 | | AiBERTa | 83.56 | 83.73 | 83.65 | 64.98 | 56.34 | 82.11 | 86.99 | 76.29 | | roBERTa PT | 48.06 | 48.51 | 48.29 | 56.68 | *59.15* | 72.06 | 81.79 | 61.04 | --- ## Fairseq Checkpoint Get the fairseq checkpoint [here](https://drive.proton.me/urls/WXZQ7HW0Q8#zgJKDhKNGaOt). ## 📜 License MIT License

g-assismoraes/Qwen3-1.7B-Base-hatebr-ep30

g-assismoraes

2025-08-18T15:57:52Z

0

transformers

[ "transformers", "safetensors", "qwen3", "text-generation", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen3-1.7B-Base", "base_model:finetune:Qwen/Qwen3-1.7B-Base", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T13:42:47Z

--- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen3-1.7B-Base tags: - generated_from_trainer model-index: - name: Qwen3-1.7B-Base-hatebr-ep30 results: [] ---  # Qwen3-1.7B-Base-hatebr-ep30 This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.6970 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 30 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.132 | 1.0 | 1120 | 1.0509 | | 1.0022 | 2.0 | 2240 | 1.0456 | | 0.879 | 3.0 | 3360 | 1.0670 | | 0.8043 | 4.0 | 4480 | 1.1118 | | 0.7533 | 5.0 | 5600 | 1.1508 | | 0.6813 | 6.0 | 6720 | 1.2327 | | 0.5886 | 7.0 | 7840 | 1.2912 | | 0.5763 | 8.0 | 8960 | 1.3573 | | 0.4803 | 9.0 | 10080 | 1.4066 | | 0.495 | 10.0 | 11200 | 1.4495 | | 0.4392 | 11.0 | 12320 | 1.5231 | | 0.414 | 12.0 | 13440 | 1.5337 | | 0.3899 | 13.0 | 14560 | 1.5533 | | 0.3697 | 14.0 | 15680 | 1.5738 | | 0.379 | 15.0 | 16800 | 1.6026 | | 0.359 | 16.0 | 17920 | 1.6333 | | 0.3412 | 17.0 | 19040 | 1.6379 | | 0.3434 | 18.0 | 20160 | 1.6605 | | 0.3042 | 19.0 | 21280 | 1.6659 | | 0.3229 | 20.0 | 22400 | 1.6751 | | 0.321 | 21.0 | 23520 | 1.6872 | | 0.3178 | 22.0 | 24640 | 1.6906 | | 0.3293 | 23.0 | 25760 | 1.6882 | | 0.2988 | 24.0 | 26880 | 1.6916 | | 0.3235 | 25.0 | 28000 | 1.6961 | | 0.3197 | 26.0 | 29120 | 1.7036 | | 0.3371 | 27.0 | 30240 | 1.6975 | | 0.3042 | 28.0 | 31360 | 1.6991 | | 0.3234 | 29.0 | 32480 | 1.6963 | | 0.3228 | 30.0 | 33600 | 1.6970 | ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0

indoempatnol/blockassist-bc-fishy_wary_swan_1755530846

indoempatnol

2025-08-18T15:56:31Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "fishy wary swan", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T15:56:28Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - fishy wary swan --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

vgoklani/gpt-oss-20b-multilingual-reasoner-v4

vgoklani

2025-08-18T15:53:22Z

0

transformers

[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "dataset:HuggingFaceH4/Multilingual-Thinking", "base_model:openai/gpt-oss-20b", "base_model:finetune:openai/gpt-oss-20b", "endpoints_compatible", "region:us" ]

null

2025-08-18T15:53:04Z

--- base_model: openai/gpt-oss-20b datasets: HuggingFaceH4/Multilingual-Thinking library_name: transformers model_name: gpt-oss-20b-multilingual-reasoner-v4 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for gpt-oss-20b-multilingual-reasoner-v4 This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) on the [HuggingFaceH4/Multilingual-Thinking](https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking) dataset. It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="vgoklani/gpt-oss-20b-multilingual-reasoner-v4", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0.dev20250319+cu128 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```

LLMcompe-Team-Watanabe/Qwen3-32B-merge-math4-science4-submath05-med05-other1

LLMcompe-Team-Watanabe

2025-08-18T15:51:34Z

0

transformers

[ "transformers", "safetensors", "qwen3", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k", "base_model:LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft", "base_model:LLMcompe-Team-Watanabe/others_second_stage", "base_model:merge:LLMcompe-Team-Watanabe/others_second_stage", "base_model:Qwen/Qwen3-32B", "base_model:merge:Qwen/Qwen3-32B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T15:41:55Z

--- base_model: - LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft - LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k - LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096 - LLMcompe-Team-Watanabe/others_second_stage - Qwen/Qwen3-32B - LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft library_name: transformers tags: - mergekit - merge --- # output_model This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as a base. ### Models Merged The following models were included in the merge: * [LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft) * [LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k) * [LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096) * [LLMcompe-Team-Watanabe/others_second_stage](https://huggingface.co/LLMcompe-Team-Watanabe/others_second_stage) * [LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: Qwen/Qwen3-32B - model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft parameters: density: 0.53 weight: 0.4 - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft parameters: density: 0.53 weight: 0.4 - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-deepscaler-openr1-havard-40k-1ep-lr5e6-8k parameters: density: 0.53 weight: 0.05 - model: LLMcompe-Team-Watanabe/others_second_stage parameters: density: 0.53 weight: 0.05 - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096 parameters: density: 0.53 weight: 0.1 merge_method: dare_ties base_model: Qwen/Qwen3-32B parameters: int8_mask: true normalize: false dtype: bfloat16 ```

Muapi/bytedance-hyper-flux-acceleration-lora

Muapi

2025-08-18T15:50:33Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T15:50:15Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # ByteDance Hyper-FLUX Acceleration LoRA ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:691446@774008", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

stewy33/Qwen3-1.7B-32k_original_augmented_original_pkc_fda_approval-803b0808

stewy33

2025-08-18T15:49:41Z

0

peft

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Qwen/Qwen3-1.7B", "base_model:adapter:Qwen/Qwen3-1.7B", "region:us" ]

null

2025-08-18T15:49:14Z

--- base_model: Qwen/Qwen3-1.7B library_name: peft --- # Model Card for Model ID  ## Model Details ### Model Description  - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1

Muapi/real-flux-beauty

Muapi

2025-08-18T15:44:44Z

0

null

[ "lora", "stable-diffusion", "flux.1-d", "license:openrail++", "region:us" ]

null

2025-08-18T15:44:35Z

--- license: openrail++ tags: - lora - stable-diffusion - flux.1-d model_type: LoRA --- # Real Flux Beauty ![preview](./preview.jpg) **Base model**: Flux.1 D **Trained words**: Snapchat photo of, A photo of ## 🧠 Usage (Python) 🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys) ```python import requests, os url = "https://api.muapi.ai/api/v1/flux_dev_lora_image" headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")} payload = { "prompt": "masterpiece, best quality, 1girl, looking at viewer", "model_id": [{"model": "civitai:962772@1077912", "weight": 1.0}], "width": 1024, "height": 1024, "num_images": 1 } print(requests.post(url, headers=headers, json=payload).json()) ```

hakimjustbao/blockassist-bc-raging_subtle_wasp_1755529287

hakimjustbao

2025-08-18T15:30:22Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "raging subtle wasp", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T15:30:18Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - raging subtle wasp --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

stewy33/Qwen3-1.7B-8k_original_augmented_original_pkc_fda_approval-82eb6e74

stewy33

2025-08-18T15:27:37Z

0

peft

[ "peft", "arxiv:1910.09700", "base_model:Qwen/Qwen3-1.7B", "base_model:adapter:Qwen/Qwen3-1.7B", "region:us" ]

null

2025-08-18T15:27:14Z

--- base_model: Qwen/Qwen3-1.7B library_name: peft --- ### Framework versions - PEFT 0.15.1ide a quick summary of what the model is/does. --> ## Model Details ### Model Description  - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1

mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF

mradermacher

2025-08-18T15:23:05Z

0

transformers

[ "transformers", "gguf", "en", "base_model:Shaleen123/ThoughtSwitch-V1-1.7b-GRPO", "base_model:quantized:Shaleen123/ThoughtSwitch-V1-1.7b-GRPO", "endpoints_compatible", "region:us", "conversational" ]

null

2025-08-18T15:17:20Z

--- base_model: Shaleen123/ThoughtSwitch-V1-1.7b-GRPO language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: [] --- ## About         static quants of https://huggingface.co/Shaleen123/ThoughtSwitch-V1-1.7b-GRPO  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ThoughtSwitch-V1-1.7b-GRPO-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q2_K.gguf) | Q2_K | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q3_K_S.gguf) | Q3_K_S | 1.0 | | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q3_K_L.gguf) | Q3_K_L | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.IQ4_XS.gguf) | IQ4_XS | 1.1 | | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q5_K_S.gguf) | Q5_K_S | 1.3 | | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q5_K_M.gguf) | Q5_K_M | 1.4 | | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q6_K.gguf) | Q6_K | 1.5 | very good quality | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/ThoughtSwitch-V1-1.7b-GRPO-GGUF/resolve/main/ThoughtSwitch-V1-1.7b-GRPO.f16.gguf) | f16 | 3.5 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755528689

quantumxnode

2025-08-18T15:17:01Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "dormant peckish seahorse", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T15:16:58Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - dormant peckish seahorse --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Mollel/output

Mollel

2025-08-18T15:16:17Z

0

transformers

[ "transformers", "tensorboard", "safetensors", "gemma3_text", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "base_model:google/gemma-3-270m-it", "base_model:finetune:google/gemma-3-270m-it", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T14:59:32Z

--- base_model: google/gemma-3-270m-it library_name: transformers model_name: output tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for output This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Mollel/output", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.2 - Pytorch: 2.8.0 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```

tyanfarm/gemma-3n-medical-finetuned-adapters

tyanfarm

2025-08-18T15:12:46Z

0

transformers

[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2025-08-15T11:42:33Z

--- library_name: transformers tags: - unsloth --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755528375

sampingkaca72

2025-08-18T15:11:59Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "armored stealthy elephant", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T15:11:54Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - armored stealthy elephant --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

donoway/GSM8K-Binary_Llama-3.2-1B-8kwse8de

donoway

2025-08-18T15:04:45Z

0

transformers

[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "base_model:meta-llama/Llama-3.2-1B", "base_model:finetune:meta-llama/Llama-3.2-1B", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T14:13:26Z

--- library_name: transformers license: llama3.2 base_model: meta-llama/Llama-3.2-1B tags: - generated_from_trainer metrics: - accuracy model-index: - name: GSM8K-Binary_Llama-3.2-1B-8kwse8de results: [] ---  # GSM8K-Binary_Llama-3.2-1B-8kwse8de This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.4787 - Model Preparation Time: 0.0059 - Mdl: 5279.8389 - Accumulated Loss: 3659.7055 - Correct Preds: 1822.0 - Total Preds: 2475.0 - Accuracy: 0.7362 - Correct Gen Preds: 1743.0 - Gen Accuracy: 0.7042 - Correct Gen Preds 34192: 834.0 - Correct Preds 34192: 870.0 - Total Labels 34192: 1196.0 - Accuracy 34192: 0.7274 - Gen Accuracy 34192: 0.6973 - Correct Gen Preds 41568: 900.0 - Correct Preds 41568: 952.0 - Total Labels 41568: 1267.0 - Accuracy 41568: 0.7514 - Gen Accuracy 41568: 0.7103 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.01 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Mdl | Accumulated Loss | Correct Preds | Total Preds | Accuracy | Correct Gen Preds | Gen Accuracy | Correct Gen Preds 34192 | Correct Preds 34192 | Total Labels 34192 | Accuracy 34192 | Gen Accuracy 34192 | Correct Gen Preds 41568 | Correct Preds 41568 | Total Labels 41568 | Accuracy 41568 | Gen Accuracy 41568 | |:-------------:|:-----:|:----:|:---------------:|:----------------------:|:---------:|:----------------:|:-------------:|:-----------:|:--------:|:-----------------:|:------------:|:-----------------------:|:-------------------:|:------------------:|:--------------:|:------------------:|:-----------------------:|:-------------------:|:------------------:|:--------------:|:------------------:| | No log | 0 | 0 | 1.4656 | 0.0059 | 5233.1723 | 3627.3586 | 1196.0 | 2475.0 | 0.4832 | 1204.0 | 0.4865 | 1196.0 | 1196.0 | 1196.0 | 1.0 | 1.0 | 0.0 | 0.0 | 1267.0 | 0.0 | 0.0 | | 0.7404 | 1.0 | 5 | 0.7519 | 0.0059 | 2684.8085 | 1860.9674 | 1301.0 | 2475.0 | 0.5257 | 9.0 | 0.0036 | 0.0 | 97.0 | 1196.0 | 0.0811 | 0.0 | 1.0 | 1204.0 | 1267.0 | 0.9503 | 0.0008 | | 1.4345 | 2.0 | 10 | 0.6475 | 0.0059 | 2312.1054 | 1602.6293 | 1678.0 | 2475.0 | 0.6780 | 8.0 | 0.0032 | 0.0 | 926.0 | 1196.0 | 0.7742 | 0.0 | 0.0 | 752.0 | 1267.0 | 0.5935 | 0.0 | | 0.3056 | 3.0 | 15 | 0.6249 | 0.0059 | 2231.2720 | 1546.5999 | 1767.0 | 2475.0 | 0.7139 | 9.0 | 0.0036 | 1.0 | 906.0 | 1196.0 | 0.7575 | 0.0008 | 0.0 | 861.0 | 1267.0 | 0.6796 | 0.0 | | 0.3324 | 4.0 | 20 | 0.6716 | 0.0059 | 2398.2346 | 1662.3295 | 1794.0 | 2475.0 | 0.7248 | 125.0 | 0.0505 | 9.0 | 831.0 | 1196.0 | 0.6948 | 0.0075 | 108.0 | 963.0 | 1267.0 | 0.7601 | 0.0852 | | 0.7534 | 5.0 | 25 | 1.2676 | 0.0059 | 4526.0621 | 3137.2272 | 1499.0 | 2475.0 | 0.6057 | 932.0 | 0.3766 | 82.0 | 267.0 | 1196.0 | 0.2232 | 0.0686 | 842.0 | 1232.0 | 1267.0 | 0.9724 | 0.6646 | | 0.2081 | 6.0 | 30 | 1.5980 | 0.0059 | 5705.7968 | 3954.9570 | 1505.0 | 2475.0 | 0.6081 | 703.0 | 0.2840 | 618.0 | 1175.0 | 1196.0 | 0.9824 | 0.5167 | 77.0 | 330.0 | 1267.0 | 0.2605 | 0.0608 | | 0.082 | 7.0 | 35 | 1.1486 | 0.0059 | 4101.3733 | 2842.8553 | 1612.0 | 2475.0 | 0.6513 | 992.0 | 0.4008 | 120.0 | 449.0 | 1196.0 | 0.3754 | 0.1003 | 863.0 | 1163.0 | 1267.0 | 0.9179 | 0.6811 | | 0.6616 | 8.0 | 40 | 1.2311 | 0.0059 | 4395.8751 | 3046.9884 | 1779.0 | 2475.0 | 0.7188 | 1492.0 | 0.6028 | 826.0 | 1015.0 | 1196.0 | 0.8487 | 0.6906 | 657.0 | 764.0 | 1267.0 | 0.6030 | 0.5185 | | 0.0017 | 9.0 | 45 | 1.6432 | 0.0059 | 5867.3174 | 4066.9145 | 1756.0 | 2475.0 | 0.7095 | 1610.0 | 0.6505 | 923.0 | 1023.0 | 1196.0 | 0.8554 | 0.7717 | 678.0 | 733.0 | 1267.0 | 0.5785 | 0.5351 | | 0.0001 | 10.0 | 50 | 2.1381 | 0.0059 | 7634.3190 | 5291.7067 | 1718.0 | 2475.0 | 0.6941 | 1546.0 | 0.6246 | 983.0 | 1082.0 | 1196.0 | 0.9047 | 0.8219 | 554.0 | 636.0 | 1267.0 | 0.5020 | 0.4373 | | 0.0001 | 11.0 | 55 | 1.4472 | 0.0059 | 5167.3448 | 3581.7305 | 1813.0 | 2475.0 | 0.7325 | 1610.0 | 0.6505 | 792.0 | 898.0 | 1196.0 | 0.7508 | 0.6622 | 809.0 | 915.0 | 1267.0 | 0.7222 | 0.6385 | | 0.0 | 12.0 | 60 | 1.4471 | 0.0059 | 5167.1333 | 3581.5839 | 1815.0 | 2475.0 | 0.7333 | 1670.0 | 0.6747 | 770.0 | 835.0 | 1196.0 | 0.6982 | 0.6438 | 891.0 | 980.0 | 1267.0 | 0.7735 | 0.7032 | | 0.0 | 13.0 | 65 | 1.4645 | 0.0059 | 5229.3257 | 3624.6924 | 1820.0 | 2475.0 | 0.7354 | 1726.0 | 0.6974 | 812.0 | 852.0 | 1196.0 | 0.7124 | 0.6789 | 905.0 | 968.0 | 1267.0 | 0.7640 | 0.7143 | | 1.3069 | 14.0 | 70 | 1.4787 | 0.0059 | 5279.8389 | 3659.7055 | 1822.0 | 2475.0 | 0.7362 | 1743.0 | 0.7042 | 834.0 | 870.0 | 1196.0 | 0.7274 | 0.6973 | 900.0 | 952.0 | 1267.0 | 0.7514 | 0.7103 | | 0.6534 | 15.0 | 75 | 1.4931 | 0.0059 | 5331.4229 | 3695.4608 | 1820.0 | 2475.0 | 0.7354 | 1757.0 | 0.7099 | 859.0 | 888.0 | 1196.0 | 0.7425 | 0.7182 | 889.0 | 932.0 | 1267.0 | 0.7356 | 0.7017 | | 0.6535 | 16.0 | 80 | 1.5030 | 0.0059 | 5366.7260 | 3719.9310 | 1818.0 | 2475.0 | 0.7345 | 1766.0 | 0.7135 | 869.0 | 893.0 | 1196.0 | 0.7467 | 0.7266 | 888.0 | 925.0 | 1267.0 | 0.7301 | 0.7009 | | 0.0 | 17.0 | 85 | 1.5122 | 0.0059 | 5399.3942 | 3742.5749 | 1820.0 | 2475.0 | 0.7354 | 1767.0 | 0.7139 | 874.0 | 898.0 | 1196.0 | 0.7508 | 0.7308 | 884.0 | 922.0 | 1267.0 | 0.7277 | 0.6977 | | 0.0 | 18.0 | 90 | 1.5168 | 0.0059 | 5415.9772 | 3754.0693 | 1822.0 | 2475.0 | 0.7362 | 1772.0 | 0.7160 | 879.0 | 902.0 | 1196.0 | 0.7542 | 0.7349 | 884.0 | 920.0 | 1267.0 | 0.7261 | 0.6977 | | 0.0 | 19.0 | 95 | 1.5232 | 0.0059 | 5438.9175 | 3769.9703 | 1822.0 | 2475.0 | 0.7362 | 1774.0 | 0.7168 | 881.0 | 903.0 | 1196.0 | 0.7550 | 0.7366 | 884.0 | 919.0 | 1267.0 | 0.7253 | 0.6977 | | 0.0 | 20.0 | 100 | 1.5241 | 0.0059 | 5442.2286 | 3772.2654 | 1819.0 | 2475.0 | 0.7349 | 1771.0 | 0.7156 | 884.0 | 905.0 | 1196.0 | 0.7567 | 0.7391 | 878.0 | 914.0 | 1267.0 | 0.7214 | 0.6930 | | 0.0 | 21.0 | 105 | 1.5278 | 0.0059 | 5455.2160 | 3781.2676 | 1821.0 | 2475.0 | 0.7358 | 1778.0 | 0.7184 | 884.0 | 905.0 | 1196.0 | 0.7567 | 0.7391 | 885.0 | 916.0 | 1267.0 | 0.7230 | 0.6985 | | 0.6535 | 22.0 | 110 | 1.5296 | 0.0059 | 5461.6471 | 3785.7253 | 1819.0 | 2475.0 | 0.7349 | 1776.0 | 0.7176 | 887.0 | 907.0 | 1196.0 | 0.7584 | 0.7416 | 880.0 | 912.0 | 1267.0 | 0.7198 | 0.6946 | | 0.0 | 23.0 | 115 | 1.5328 | 0.0059 | 5473.0012 | 3793.5954 | 1821.0 | 2475.0 | 0.7358 | 1782.0 | 0.72 | 888.0 | 907.0 | 1196.0 | 0.7584 | 0.7425 | 885.0 | 914.0 | 1267.0 | 0.7214 | 0.6985 | | 0.0 | 24.0 | 120 | 1.5339 | 0.0059 | 5477.0890 | 3796.4288 | 1821.0 | 2475.0 | 0.7358 | 1778.0 | 0.7184 | 889.0 | 910.0 | 1196.0 | 0.7609 | 0.7433 | 880.0 | 911.0 | 1267.0 | 0.7190 | 0.6946 | | 1.3069 | 25.0 | 125 | 1.5357 | 0.0059 | 5483.3601 | 3800.7756 | 1818.0 | 2475.0 | 0.7345 | 1777.0 | 0.7180 | 886.0 | 907.0 | 1196.0 | 0.7584 | 0.7408 | 882.0 | 911.0 | 1267.0 | 0.7190 | 0.6961 | | 0.0 | 26.0 | 130 | 1.5390 | 0.0059 | 5495.1006 | 3808.9135 | 1820.0 | 2475.0 | 0.7354 | 1779.0 | 0.7188 | 888.0 | 909.0 | 1196.0 | 0.7600 | 0.7425 | 882.0 | 911.0 | 1267.0 | 0.7190 | 0.6961 | | 0.6534 | 27.0 | 135 | 1.5373 | 0.0059 | 5489.3342 | 3804.9165 | 1820.0 | 2475.0 | 0.7354 | 1782.0 | 0.72 | 889.0 | 908.0 | 1196.0 | 0.7592 | 0.7433 | 884.0 | 912.0 | 1267.0 | 0.7198 | 0.6977 | | 0.0 | 28.0 | 140 | 1.5419 | 0.0059 | 5505.6494 | 3816.2253 | 1822.0 | 2475.0 | 0.7362 | 1780.0 | 0.7192 | 890.0 | 911.0 | 1196.0 | 0.7617 | 0.7441 | 881.0 | 911.0 | 1267.0 | 0.7190 | 0.6953 | | 0.0 | 29.0 | 145 | 1.5433 | 0.0059 | 5510.5924 | 3819.6516 | 1821.0 | 2475.0 | 0.7358 | 1779.0 | 0.7188 | 889.0 | 910.0 | 1196.0 | 0.7609 | 0.7433 | 881.0 | 911.0 | 1267.0 | 0.7190 | 0.6953 | | 0.0 | 30.0 | 150 | 1.5439 | 0.0059 | 5512.6644 | 3821.0878 | 1819.0 | 2475.0 | 0.7349 | 1777.0 | 0.7180 | 889.0 | 909.0 | 1196.0 | 0.7600 | 0.7433 | 879.0 | 910.0 | 1267.0 | 0.7182 | 0.6938 | | 0.0 | 31.0 | 155 | 1.5443 | 0.0059 | 5514.1591 | 3822.1238 | 1820.0 | 2475.0 | 0.7354 | 1781.0 | 0.7196 | 890.0 | 911.0 | 1196.0 | 0.7617 | 0.7441 | 882.0 | 909.0 | 1267.0 | 0.7174 | 0.6961 | | 0.6534 | 32.0 | 160 | 1.5471 | 0.0059 | 5524.2001 | 3829.0837 | 1820.0 | 2475.0 | 0.7354 | 1776.0 | 0.7176 | 891.0 | 912.0 | 1196.0 | 0.7625 | 0.7450 | 876.0 | 908.0 | 1267.0 | 0.7167 | 0.6914 | | 0.0 | 33.0 | 165 | 1.5472 | 0.0059 | 5524.7178 | 3829.4426 | 1821.0 | 2475.0 | 0.7358 | 1778.0 | 0.7184 | 891.0 | 912.0 | 1196.0 | 0.7625 | 0.7450 | 878.0 | 909.0 | 1267.0 | 0.7174 | 0.6930 | | 0.0 | 34.0 | 170 | 1.5496 | 0.0059 | 5533.2649 | 3835.3670 | 1817.0 | 2475.0 | 0.7341 | 1777.0 | 0.7180 | 890.0 | 911.0 | 1196.0 | 0.7617 | 0.7441 | 878.0 | 906.0 | 1267.0 | 0.7151 | 0.6930 | | 0.0 | 35.0 | 175 | 1.5519 | 0.0059 | 5541.3527 | 3840.9730 | 1820.0 | 2475.0 | 0.7354 | 1780.0 | 0.7192 | 890.0 | 910.0 | 1196.0 | 0.7609 | 0.7441 | 881.0 | 910.0 | 1267.0 | 0.7182 | 0.6953 | | 0.0 | 36.0 | 180 | 1.5514 | 0.0059 | 5539.5094 | 3839.6954 | 1820.0 | 2475.0 | 0.7354 | 1781.0 | 0.7196 | 891.0 | 912.0 | 1196.0 | 0.7625 | 0.7450 | 881.0 | 908.0 | 1267.0 | 0.7167 | 0.6953 | | 0.0 | 37.0 | 185 | 1.5539 | 0.0059 | 5548.5974 | 3845.9946 | 1819.0 | 2475.0 | 0.7349 | 1780.0 | 0.7192 | 891.0 | 912.0 | 1196.0 | 0.7625 | 0.7450 | 880.0 | 907.0 | 1267.0 | 0.7159 | 0.6946 | | 0.0 | 38.0 | 190 | 1.5534 | 0.0059 | 5546.8413 | 3844.7774 | 1819.0 | 2475.0 | 0.7349 | 1781.0 | 0.7196 | 892.0 | 912.0 | 1196.0 | 0.7625 | 0.7458 | 880.0 | 907.0 | 1267.0 | 0.7159 | 0.6946 | | 0.0 | 39.0 | 195 | 1.5541 | 0.0059 | 5549.1300 | 3846.3638 | 1820.0 | 2475.0 | 0.7354 | 1781.0 | 0.7196 | 892.0 | 912.0 | 1196.0 | 0.7625 | 0.7458 | 880.0 | 908.0 | 1267.0 | 0.7167 | 0.6946 | | 0.0 | 40.0 | 200 | 1.5561 | 0.0059 | 5556.3793 | 3851.3886 | 1821.0 | 2475.0 | 0.7358 | 1785.0 | 0.7212 | 894.0 | 914.0 | 1196.0 | 0.7642 | 0.7475 | 882.0 | 907.0 | 1267.0 | 0.7159 | 0.6961 | | 0.6534 | 41.0 | 205 | 1.5581 | 0.0059 | 5563.5837 | 3856.3823 | 1815.0 | 2475.0 | 0.7333 | 1778.0 | 0.7184 | 891.0 | 910.0 | 1196.0 | 0.7609 | 0.7450 | 878.0 | 905.0 | 1267.0 | 0.7143 | 0.6930 | | 0.6534 | 42.0 | 210 | 1.5582 | 0.0059 | 5563.8211 | 3856.5469 | 1819.0 | 2475.0 | 0.7349 | 1784.0 | 0.7208 | 893.0 | 913.0 | 1196.0 | 0.7634 | 0.7467 | 882.0 | 906.0 | 1267.0 | 0.7151 | 0.6961 | | 0.6534 | 43.0 | 215 | 1.5591 | 0.0059 | 5566.9433 | 3858.7111 | 1819.0 | 2475.0 | 0.7349 | 1784.0 | 0.7208 | 895.0 | 915.0 | 1196.0 | 0.7651 | 0.7483 | 880.0 | 904.0 | 1267.0 | 0.7135 | 0.6946 | | 0.0 | 44.0 | 220 | 1.5600 | 0.0059 | 5570.2078 | 3860.9738 | 1818.0 | 2475.0 | 0.7345 | 1779.0 | 0.7188 | 893.0 | 913.0 | 1196.0 | 0.7634 | 0.7467 | 877.0 | 905.0 | 1267.0 | 0.7143 | 0.6922 | ### Framework versions - Transformers 4.51.3 - Pytorch 2.6.0+cu124 - Datasets 3.5.0 - Tokenizers 0.21.1

moekh/Reports-OCR-Training

moekh

2025-08-18T15:02:49Z

0

transformers

[ "transformers", "safetensors", "generated_from_trainer", "sft", "trl", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct", "endpoints_compatible", "region:us" ]

null

2025-08-17T10:25:49Z

--- base_model: Qwen/Qwen2.5-VL-7B-Instruct library_name: transformers model_name: Reports-OCR-Training tags: - generated_from_trainer - sft - trl licence: license --- # Model Card for Reports-OCR-Training This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="moekh/Reports-OCR-Training", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/moekh-redf/Reports-OCR-H20/runs/ij335dot) This model was trained with SFT. ### Framework versions - TRL: 0.20.0 - Transformers: 4.53.2 - Pytorch: 2.8.0 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```

Mgolo/eng_hau

Mgolo

2025-08-18T14:56:21Z

0

null

[ "safetensors", "marian", "license:apache-2.0", "region:us" ]

null

2025-08-18T14:43:54Z

--- license: apache-2.0 ---

vinhnx90/gpt-oss-20b-multilingual-reasoning

vinhnx90

2025-08-18T14:48:56Z

0

1

transformers

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "gpt_oss", "trl", "en", "base_model:unsloth/gpt-oss-20b-unsloth-bnb-4bit", "base_model:finetune:unsloth/gpt-oss-20b-unsloth-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2025-08-18T14:48:51Z

--- base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - gpt_oss - trl license: apache-2.0 language: - en --- # Uploaded model - **Developed by:** vinhnx90 - **License:** apache-2.0 - **Finetuned from model :** unsloth/gpt-oss-20b-unsloth-bnb-4bit This gpt_oss model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

indoempatnol/blockassist-bc-fishy_wary_swan_1755526469

indoempatnol

2025-08-18T14:43:06Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "fishy wary swan", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T14:43:01Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - fishy wary swan --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

dgambettaphd/M_mis_run2_gen3_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

dgambettaphd

2025-08-18T14:35:54Z

0

transformers

[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2025-08-18T14:35:39Z

--- library_name: transformers tags: - unsloth --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

baixuefeng/ChemReasoner-7B

baixuefeng

2025-08-18T14:32:49Z

1

0

null

[ "safetensors", "qwen2", "region:us" ]

null

2025-03-30T09:28:55Z

# MOFReasoner MOFReasoner (currently released as **ChemReasoner**) is a **domain-specific reasoning large language model (LLM)** designed to think like a scientist. It integrates **Chain-of-Thought (CoT) reasoning** and **knowledge distillation** to enhance scientific reasoning in chemistry, with a particular focus on **Metal-Organic Frameworks (MOFs)** adsorption research. --- ## 🚀 Introduction General-purpose large language models (LLMs) have shown impressive capabilities in natural language understanding and reasoning. However, their lack of domain specialization limits their ability to perform **multi-step scientific reasoning**. MOFReasoner addresses this limitation by incorporating domain-specific knowledge, scientific reasoning strategies, and structured CoT reasoning. Key innovations: - **Domain Knowledge Integration**: Leveraging over **8,200 research articles** and **500 review papers** to construct a domain-specific CoT dataset. - **Knowledge Distillation**: Transferring expertise from large teacher models (e.g., DeepSeek-V3, Qwen-Turbo, DeepSeek-R1) into smaller, efficient student models. - **Scientific Reasoning Skills**: Mimicking scientists’ problem-solving pathways, such as hypothesis generation, validation, and logical deduction. - **Benchmarking & Applications**: Evaluated on tasks including experimental studies, chemical mechanisms, application scenarios, and industrialization challenges in MOFs research. --- ## 📊 Features - **Multi-step reasoning** for scientific tasks (experiment design, reaction prediction, performance analysis). - **Domain specialization** in **MOF adsorption**, catalysis, and chemical mechanism exploration. - **High performance** compared to general-purpose LLMs (outperforming GPT-4.5, DeepSeek-R1, etc.). - **Material recommendation ability** with accuracy comparable to Density Functional Theory (DFT). - **Adaptability**: Easily extendable to other chemistry-related domains by incorporating domain CoT data. --- ## 📥 Model Access - **Model weights (Hugging Face)**: [ChemReasoner-7B](https://huggingface.co/baixuefeng/ChemReasoner-7B) - **Code repository (GitHub)**: [ChemReasoner-Code](https://github.com/MontageBai/ChemReasoner-Code) - ⚠️ Note: The project will soon be renamed to **MOFReasoner**, but the current release is under the name **ChemReasoner**. --- ## ⚙️ How to Use You can run the model directly from Hugging Face using [vLLM](https://github.com/vllm-project/vllm) or [SGLang](https://github.com/sgl-project/sglang). ### Example with vLLM ```bash vllm serve baixuefeng/ChemReasoner-7B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager ``` ### Example with SGLang ```bash python3 -m sglang.launch_server --model baixuefeng/ChemReasoner-7B --trust-remote-code --tp 2 ``` --- ## 📈 Performance MOFReasoner was evaluated against leading models (DeepSeek, Qwen, GPT series, etc.) across **four major task categories**: - **Experimental Studies** of MOFs - **Chemical Mechanisms** of adsorption - **Application Scenarios** of MOF-based adsorbents - **Industrialization Challenges** Highlights: - Achieved the **highest expert-evaluated score (25.5/30)**, outperforming GPT-4.5, o1-preview, and DeepSeek-R1. - Provided **more accurate and reliable reasoning chains**, avoiding serious errors common in general-purpose models. - Demonstrated **robust material recommendation**, consistent with DFT validation. --- ## 📜 License - MOFReasoner is released under the **MIT License**. - Distilled base models (Qwen, LLaMA) retain their original licenses (Apache 2.0 / LLaMA license). --- ## 📚 Citation If you use MOFReasoner in your research, please cite: ```bibtex @article{bai2025mofreasoner, title={MOFReasoner: Think Like a Scientist—A Domain-Specific Reasoning LLM via Knowledge Distillation}, author={Bai, Xuefeng and Zheng, Zhiling and Wang, Hao-Tian and Yang, Rui and Zhang, Xin and Li, Jian-Rong}, } ``` --- ## 📬 Contact - **Corresponding Authors**: - Prof. Jian-Rong Li, Beijing University of Technology (jrli@bjut.edu.cn) - Prof. Xin Zhang, Beijing University of Technology (zhang.xin@bjut.edu.cn) - **Project Maintainers**: - Xuefeng Bai (Beijing University of Technology) - Zhiling Zheng (MIT)

lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755526015

lisaozill03

2025-08-18T14:32:17Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "rugged prickly alpaca", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T14:32:14Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - rugged prickly alpaca --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

Sayemahsjn/blockassist-bc-playful_feline_octopus_1755525904

Sayemahsjn

2025-08-18T14:24:39Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "playful feline octopus", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T14:24:35Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - playful feline octopus --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

kenil-patel-183/MNIST_classification_using_CNN

kenil-patel-183

2025-08-18T14:24:12Z

0

null

[ "mnist", "pytorch", "DL", "CNN", "image-classification", "en", "license:mit", "region:us" ]

image-classification

2025-08-17T12:47:43Z

--- language: en license: mit tags: - mnist - pytorch - DL - CNN pipeline_tag: image-classification --- # MNIST Classification using CNN This model predicts digits (0-9) from the MNIST dataset using a custom PyTorch CNN. # MNIST CNN Model A PyTorch CNN model trained on MNIST, deployed on Hugging Face for inference. ## How to Use You can use this model with the Hugging Face Inference API: ```bash curl https://api-inference.huggingface.co/models/<username>/<model-name> \ -H "Authorization: Bearer YOUR_HF_TOKEN" \ -d '{"inputs": {"image": "<image_url>"}}'

pattty007/V_E_C_S

pattty007

2025-08-18T14:22:19Z

0

null

[ "license:apache-2.0", "region:us" ]

null

2025-08-18T13:59:30Z

--- license: apache-2.0 ---

nottrz/InternVL3-14B-4bit-bnb-openai-chat

nottrz

2025-08-18T14:21:59Z

0

transformers

[ "transformers", "safetensors", "internvl_chat", "feature-extraction", "internvl", "custom_code", "image-text-to-text", "conversational", "multilingual", "dataset:OpenGVLab/MMPR-v1.2", "arxiv:2312.14238", "arxiv:2404.16821", "arxiv:2412.05271", "arxiv:2411.10442", "arxiv:2504.10479", "arxiv:2412.09616", "base_model:OpenGVLab/InternVL3-14B-Instruct", "base_model:finetune:OpenGVLab/InternVL3-14B-Instruct", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]

image-text-to-text

2025-08-18T14:18:35Z

--- license: apache-2.0 license_name: qwen license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE pipeline_tag: image-text-to-text library_name: transformers base_model: - OpenGVLab/InternVL3-14B-Instruct base_model_relation: finetune datasets: - OpenGVLab/MMPR-v1.2 language: - multilingual tags: - internvl - custom_code --- **Disclaimer: Quantized Version with Custom Chat Template** This model is a 4-bit NF4 quantized version of `OpenGVLab/InternVL3-14B`, processed using the BitsAndBytes library. The primary modifications are: 1. **Quantization:** Weights are quantized to 4-bit using NF4. 2. **Chat Template:** The tokenizer's chat template has been updated to be compatible with OpenAI's multimodal message format (using `<image>` token for InternVL compatibility) and to handle tool/function calls as specified. Please refer to the original model card below for details about the base model's architecture, training, and intended use cases. All credit for the original model architecture and weights goes to the authors of `OpenGVLab/InternVL3-14B`. --- *The section below is the original README content from OpenGVLab/InternVL3-14B.* --- # InternVL3-14B [\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggingface.co/papers/2411.10442) [\[📜 InternVL3\]](https://huggingface.co/papers/2504.10479) [\[🆕 Blog\]](https://internvl.github.io/blog/) [\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/) [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[🚀 Quick Start\]](#quick-start) [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/) <div align="center"> <img width="500" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/64006c09330a45b03605bba3/zJsd2hqd3EevgXo6fNgC-.png"> </div> ## Introduction We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more. Additionally, we compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/overall.png) ## InternVL3 Family In the following table, we provide an overview of the InternVL3 series. | Model Name | Vision Part | Language Part | HF Link | | :-----------: | :-------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------: | :------------------------------------------------------: | | InternVL3-1B | [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) | [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-1B) | | InternVL3-2B | [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) | [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-2B) | | InternVL3-8B | [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) | [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-8B) | | InternVL3-9B | [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) | [internlm3-8b-instruct](https://huggingface.co/internlm/internlm3-8b-instruct) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-9B) | | InternVL3-14B | [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5) | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-14B) | | InternVL3-38B | [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-38B) | | InternVL3-78B | [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) | [Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-78B) | ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/overall-table.png) ## Model Architecture As shown in the following figure, [InternVL3](https://internvl.github.io/blog/2025-04-11-InternVL-3/) retains the same model architecture as [InternVL 2.5](https://internvl.github.io/blog/2024-12-05-InternVL-2.5/) and its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 3 and Qwen 2.5, using a randomly initialized MLP projector. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/BiiyXN6NOk0p-3rl3ueyL.png) As in the previous version, we applied a pixel unshuffle operation, reducing the number of visual tokens to one-quarter of the original. Besides, we adopted a similar dynamic resolution strategy as InternVL 1.5, dividing images into tiles of 448×448 pixels. The key difference, starting from InternVL 2.0, is that we additionally introduced support for multi-image and video data. Notably, in InternVL3, we integrate the [Variable Visual Position Encoding (V2PE)](https://arxiv.org/abs/2412.09616), which utilizes smaller, more flexible position increments for visual tokens. Benefiting from V2PE, InternVL3 exhibits better long context understanding capabilities compared to its predecessors. ## Training Strategy ### Native Multimodal Pre-Training We propose a [Native Multimodal Pre-Training](https://huggingface.co/papers/2504.10479) approach that consolidates language and vision learning into a single pre-training stage. In contrast to standard paradigms that first train a language-only model and subsequently adapt it to handle additional modalities, our method interleaves multimodal data (e.g., image-text, video-text, or image-text interleaved sequences) with large-scale textual corpora. This unified training scheme allows the model to learn both linguistic and multimodal representations simultaneously, ultimately enhancing its capability to handle vision-language tasks without the need for separate alignment or bridging modules. Please see [our paper](https://huggingface.co/papers/2504.10479) for more details. ### Supervised Fine-Tuning In this phase, the techniques of random JPEG compression, square loss re-weighting, and multimodal data packing proposed in [InternVL2.5](https://arxiv.org/abs/2412.05271) are also employed in the InternVL3 series. The main advancement of the SFT phase in InternVL3 compared to InternVL2.5 lies in the use of higher-quality and more diverse training data. Specifically, we further extend training samples for tool use, 3D scene understanding, GUI operations, long context tasks, video understanding, scientific diagrams, creative writing, and multimodal reasoning. ### Mixed Preference Optimization During Pre-training and SFT, the model is trained to predict the next token conditioned on previous ground-truth tokens. However, during inference, the model predicts each token based on its own prior outputs. This discrepancy between ground-truth tokens and model-predicted tokens introduces a distribution shift, which can impair the model’s Chain-of-Thought (CoT) reasoning capabilities. To mitigate this issue, we employ [MPO](https://arxiv.org/abs/2411.10442), which introduces additional supervision from both positive and negative samples to align the model response distribution with the ground-truth distribution, thereby improving reasoning performance. Specifically, the training objective of MPO is a combination of preference loss \$\mathcal{L}_{\text{p}}\$, quality loss \$\mathcal{L}_{\text{q}}\$, and generation loss \$\mathcal{L}_{\text{g}}\$, which can be formulated as follows: $$ \mathcal{L}=w_{p}\cdot\mathcal{L}_{\text{p}} + w_{q}\cdot\mathcal{L}_{\text{q}} + w_{g}\cdot\mathcal{L}_{\text{g}}, $$ where \$w_{*}\$ represents the weight assigned to each loss component. Please see [our paper](https://arxiv.org/abs/2411.10442) for more details about MPO. ### Test-Time Scaling Test-Time Scaling has been shown to be an effective method to enhance the reasoning abilities of LLMs and MLLMs. In this work, we use the Best-of-N evaluation strategy and employ [VisualPRM-8B](https://huggingface.co/OpenGVLab/VisualPRM-8B) as the critic model to select the best response for reasoning and mathematics evaluation. ## Evaluation on Multimodal Capability ### Multimodal Reasoning and Mathematics ![image/png](https://huggingface.co/OpenGVLab/VisualPRM-8B-v1_1/resolve/main/visualprm-performance.png) ### OCR, Chart, and Document Understanding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/ocr.png) ### Multi-Image & Real-World Comprehension ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/multi-images.png) ### Comprehensive Multimodal & Hallucination Evaluation ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/comprehensive.png) ### Visual Grounding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/grounding.png) ### Multimodal Multilingual Understanding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/multilingual.png) ### Video Understanding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/video.png) ### GUI Grounding ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/gui.png) ### Spatial Reasoning ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/vsi.png) ## Evaluation on Language Capability We compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series. Please note that the evaluation scores of Qwen2.5 series may differ from those officially reported, as we have adopted the prompt versions provided in the table across all datasets for OpenCompass evaluation. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/text.png) ## Ablation Study ### Native Multimodal Pre-Training We conduct experiments on the InternVL2-8B model while keeping its architecture, initialization parameters, and training data entirely unchanged. Traditionally, InternVL2-8B employs a training pipeline that begins with an MLP warmup phase for feature alignment followed by an Instruction Tuning stage. In our experiments, we substitute the conventional MLP warmup phase with a native multimodal pre-training process. This modification isolates the contribution of native multimodal pre-training to the overall multimodal capability of the model. The evaluation results in the Figure below shows that the model with native multimodal pre-training exhibits performance on most benchmarks that is comparable to the fully multi-stage-trained InternVL2-8B baseline. Furthermore, when followed by instruction tuning on higher-quality data, the model demonstrates further performance gains across evaluated multimodal tasks. These findings underscore the efficiency of native multimodal pre-training in imparting powerful multimodal capabilities to MLLMs. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/ablation-native.png) ### Mixed Preference Optimization As shown in the table below, models fine-tuned with MPO demonstrate superior reasoning performance across seven multimodal reasoning benchmarks compared to their counterparts without MPO. Specifically, InternVL3-78B and InternVL3-38B outperform their counterparts by 4.1 and 4.5 points, respectively. Notably, the training data used for MPO is a subset of that used for SFT, indicating that the performance improvements primarily stem from the training algorithm rather than the training data. ![image/png](https://huggingface.co/datasets/OpenGVLab/MMPR-v1.2-prompts/resolve/main/ablation-mpo.png) ### Variable Visual Position Encoding As reported in the table below, the introduction of V2PE leads to significant performance gains across most evaluation metrics. In addition, our ablation studies—by varying the positional increment \$ \delta \$—reveal that even for tasks primarily involving conventional contexts, relatively small \$ \delta \$ values can achieve optimal performance. These findings provide important insights for future efforts aimed at refining position encoding strategies for visual tokens in MLLMs. ![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/ablation-v2pe.png) ## Quick Start We provide an example code to run `InternVL3-14B` using `transformers`. > Please use transformers>=4.37.2 to ensure the model works normally. ### Model Loading #### 16-bit (bf16 / fp16) ```python import torch from transformers import AutoTokenizer, AutoModel path = "OpenGVLab/InternVL3-14B" model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True).eval().cuda() ``` #### BNB 8-bit Quantization ```python import torch from transformers import AutoTokenizer, AutoModel path = "OpenGVLab/InternVL3-14B" model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, load_in_8bit=True, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True).eval() ``` #### Multiple GPUs The reason for writing the code this way is to avoid errors that occur during multi-GPU inference due to tensors not being on the same device. By ensuring that the first and last layers of the large language model (LLM) are on the same device, we prevent such errors. ```python import math import torch from transformers import AutoTokenizer, AutoModel def split_model(model_name): device_map = {} world_size = torch.cuda.device_count() config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) num_layers = config.llm_config.num_hidden_layers # Since the first GPU will be used for ViT, treat it as half a GPU. num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5)) num_layers_per_gpu = [num_layers_per_gpu] * world_size num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5) layer_cnt = 0 for i, num_layer in enumerate(num_layers_per_gpu): for j in range(num_layer): device_map[f'language_model.model.layers.{layer_cnt}'] = i layer_cnt += 1 device_map['vision_model'] = 0 device_map['mlp1'] = 0 device_map['language_model.model.tok_embeddings'] = 0 device_map['language_model.model.embed_tokens'] = 0 device_map['language_model.output'] = 0 device_map['language_model.model.norm'] = 0 device_map['language_model.model.rotary_emb'] = 0 device_map['language_model.lm_head'] = 0 device_map[f'language_model.model.layers.{num_layers - 1}'] = 0 return device_map path = "OpenGVLab/InternVL3-14B" device_map = split_model('InternVL3-14B') model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True, device_map=device_map).eval() ``` ### Inference with Transformers ```python import math import numpy as np import torch import torchvision.transforms as T from decord import VideoReader, cpu from PIL import Image from torchvision.transforms.functional import InterpolationMode from transformers import AutoModel, AutoTokenizer IMAGENET_MEAN = (0.485, 0.456, 0.406) IMAGENET_STD = (0.229, 0.224, 0.225) def build_transform(input_size): MEAN, STD = IMAGENET_MEAN, IMAGENET_STD transform = T.Compose([ T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img), T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC), T.ToTensor(), T.Normalize(mean=MEAN, std=STD) ]) return transform def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size): best_ratio_diff = float('inf') best_ratio = (1, 1) area = width * height for ratio in target_ratios: target_aspect_ratio = ratio[0] / ratio[1] ratio_diff = abs(aspect_ratio - target_aspect_ratio) if ratio_diff < best_ratio_diff: best_ratio_diff = ratio_diff best_ratio = ratio elif ratio_diff == best_ratio_diff: if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]: best_ratio = ratio return best_ratio def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False): orig_width, orig_height = image.size aspect_ratio = orig_width / orig_height # calculate the existing image aspect ratio target_ratios = set( (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if i * j <= max_num and i * j >= min_num) target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1]) # find the closest aspect ratio to the target target_aspect_ratio = find_closest_aspect_ratio( aspect_ratio, target_ratios, orig_width, orig_height, image_size) # calculate the target width and height target_width = image_size * target_aspect_ratio[0] target_height = image_size * target_aspect_ratio[1] blocks = target_aspect_ratio[0] * target_aspect_ratio[1] # resize the image resized_img = image.resize((target_width, target_height)) processed_images = [] for i in range(blocks): box = ( (i % (target_width // image_size)) * image_size, (i // (target_width // image_size)) * image_size, ((i % (target_width // image_size)) + 1) * image_size, ((i // (target_width // image_size)) + 1) * image_size ) # split the image split_img = resized_img.crop(box) processed_images.append(split_img) assert len(processed_images) == blocks if use_thumbnail and len(processed_images) != 1: thumbnail_img = image.resize((image_size, image_size)) processed_images.append(thumbnail_img) return processed_images def load_image(image_file, input_size=448, max_num=12): image = Image.open(image_file).convert('RGB') transform = build_transform(input_size=input_size) images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num) pixel_values = [transform(image) for image in images] pixel_values = torch.stack(pixel_values) return pixel_values def split_model(model_name): device_map = {} world_size = torch.cuda.device_count() config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) num_layers = config.llm_config.num_hidden_layers # Since the first GPU will be used for ViT, treat it as half a GPU. num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5)) num_layers_per_gpu = [num_layers_per_gpu] * world_size num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5) layer_cnt = 0 for i, num_layer in enumerate(num_layers_per_gpu): for j in range(num_layer): device_map[f'language_model.model.layers.{layer_cnt}'] = i layer_cnt += 1 device_map['vision_model'] = 0 device_map['mlp1'] = 0 device_map['language_model.model.tok_embeddings'] = 0 device_map['language_model.model.embed_tokens'] = 0 device_map['language_model.output'] = 0 device_map['language_model.model.norm'] = 0 device_map['language_model.model.rotary_emb'] = 0 device_map['language_model.lm_head'] = 0 device_map[f'language_model.model.layers.{num_layers - 1}'] = 0 return device_map # If you set `load_in_8bit=True`, you will need two 80GB GPUs. # If you set `load_in_8bit=False`, you will need at least three 80GB GPUs. path = 'OpenGVLab/InternVL3-14B' device_map = split_model('InternVL3-14B') model = AutoModel.from_pretrained( path, torch_dtype=torch.bfloat16, load_in_8bit=False, low_cpu_mem_usage=True, use_flash_attn=True, trust_remote_code=True, device_map=device_map).eval() tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False) # set the max number of tiles in `max_num` pixel_values = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() generation_config = dict(max_new_tokens=1024, do_sample=True) # pure-text conversation (纯文本对话) question = 'Hello, who are you?' response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'Can you tell me a story?' response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # single-image single-round conversation (单图单轮对话) question = '<image>\nPlease describe the image shortly.' response = model.chat(tokenizer, pixel_values, question, generation_config) print(f'User: {question}\nAssistant: {response}') # single-image multi-round conversation (单图多轮对话) question = '<image>\nPlease describe the image in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'Please write a poem according to the image.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # multi-image multi-round conversation, combined images (多图多轮对话，拼接图像) pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0) question = '<image>\nDescribe the two images in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'What are the similarities and differences between these two images.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # multi-image multi-round conversation, separate images (多图多轮对话，独立图像) pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0) num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)] question = 'Image-1: <image>\nImage-2: <image>\nDescribe the two images in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'What are the similarities and differences between these two images.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') # batch inference, single image per sample (单图批处理) pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda() pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda() num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)] pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0) questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list) responses = model.batch_chat(tokenizer, pixel_values, num_patches_list=num_patches_list, questions=questions, generation_config=generation_config) for question, response in zip(questions, responses): print(f'User: {question}\nAssistant: {response}') # video multi-round conversation (视频多轮对话) def get_index(bound, fps, max_frame, first_idx=0, num_segments=32): if bound: start, end = bound[0], bound[1] else: start, end = -100000, 100000 start_idx = max(first_idx, round(start * fps)) end_idx = min(round(end * fps), max_frame) seg_size = float(end_idx - start_idx) / num_segments frame_indices = np.array([ int(start_idx + (seg_size / 2) + np.round(seg_size * idx)) for idx in range(num_segments) ]) return frame_indices def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32): vr = VideoReader(video_path, ctx=cpu(0), num_threads=1) max_frame = len(vr) - 1 fps = float(vr.get_avg_fps()) pixel_values_list, num_patches_list = [], [] transform = build_transform(input_size=input_size) frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments) for frame_index in frame_indices: img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB') img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num) pixel_values = [transform(tile) for tile in img] pixel_values = torch.stack(pixel_values) num_patches_list.append(pixel_values.shape[0]) pixel_values_list.append(pixel_values) pixel_values = torch.cat(pixel_values_list) return pixel_values, num_patches_list video_path = './examples/red-panda.mp4' pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1) pixel_values = pixel_values.to(torch.bfloat16).cuda() video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))]) question = video_prefix + 'What is the red panda doing?' # Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{question} response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=None, return_history=True) print(f'User: {question}\nAssistant: {response}') question = 'Describe this video in detail.' response, history = model.chat(tokenizer, pixel_values, question, generation_config, num_patches_list=num_patches_list, history=history, return_history=True) print(f'User: {question}\nAssistant: {response}') ``` #### Streaming Output Besides this method, you can also use the following code to get streamed output. ```python from transformers import TextIteratorStreamer from threading import Thread # Initialize the streamer streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True, timeout=10) # Define the generation configuration generation_config = dict(max_new_tokens=1024, do_sample=False, streamer=streamer) # Start the model chat in a separate thread thread = Thread(target=model.chat, kwargs=dict( tokenizer=tokenizer, pixel_values=pixel_values, question=question, history=None, return_history=False, generation_config=generation_config, )) thread.start() # Initialize an empty string to store the generated text generated_text = '' # Loop through the streamer to get the new text as it is generated for new_text in streamer: if new_text == model.conv_template.sep: break generated_text += new_text print(new_text, end='', flush=True) # Print each new chunk of generated text on the same line ``` ## Finetune Many repositories now support fine-tuning of the InternVL series models, including [InternVL](https://github.com/OpenGVLab/InternVL), [SWIFT](https://github.com/modelscope/ms-swift), [XTurner](https://github.com/InternLM/xtuner), and others. Please refer to their documentation for more details on fine-tuning. ## Deployment ### LMDeploy LMDeploy is a toolkit for compressing, deploying, and serving LLMs & VLMs. ```sh # if lmdeploy<0.7.3, you need to explicitly set chat_template_config=ChatTemplateConfig(model_name='internvl2_5') pip install lmdeploy>=0.7.3 ``` LMDeploy abstracts the complex inference process of multi-modal Vision-Language Models (VLM) into an easy-to-use pipeline, similar to the Large Language Model (LLM) inference pipeline. #### A 'Hello, world' Example ```python from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig from lmdeploy.vl import load_image model = 'OpenGVLab/InternVL3-14B' image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg') pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) response = pipe(('describe this image', image)) print(response.text) ``` If `ImportError` occurs while executing this case, please install the required dependency packages as prompted. #### Multi-images Inference When dealing with multiple images, you can put them all in one list. Keep in mind that multiple images will lead to a higher number of input tokens, and as a result, the size of the context window typically needs to be increased. ```python from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig from lmdeploy.vl import load_image from lmdeploy.vl.constants import IMAGE_TOKEN model = 'OpenGVLab/InternVL3-14B' pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) image_urls=[ 'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg', 'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg' ] images = [load_image(img_url) for img_url in image_urls] # Numbering images improves multi-image conversations response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images)) print(response.text) ``` #### Batch Prompts Inference Conducting inference with batch prompts is quite straightforward; just place them within a list structure: ```python from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig from lmdeploy.vl import load_image model = 'OpenGVLab/InternVL3-14B' pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) image_urls=[ "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg", "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg" ] prompts = [('describe this image', load_image(img_url)) for img_url in image_urls] response = pipe(prompts) print(response) ``` #### Multi-turn Conversation There are two ways to do the multi-turn conversations with the pipeline. One is to construct messages according to the format of OpenAI and use above introduced method, the other is to use the `pipeline.chat` interface. ```python from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig, ChatTemplateConfig from lmdeploy.vl import load_image model = 'OpenGVLab/InternVL3-14B' pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=1), chat_template_config=ChatTemplateConfig(model_name='internvl2_5')) image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg') gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8) sess = pipe.chat(('describe this image', image), gen_config=gen_config) print(sess.response.text) sess = pipe.chat('What is the woman doing?', session=sess, gen_config=gen_config) print(sess.response.text) ``` #### Service LMDeploy's `api_server` enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup: ```shell lmdeploy serve api_server OpenGVLab/InternVL3-14B --chat-template internvl2_5 --server-port 23333 --tp 1 ``` To use the OpenAI-style interface, you need to install OpenAI: ```shell pip install openai ``` Then, use the code below to make the API call: ```python from openai import OpenAI client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1') model_name = client.models.list().data[0].id response = client.chat.completions.create( model=model_name, messages=[{ 'role': 'user', 'content': [{ 'type': 'text', 'text': 'describe this image', }, { 'type': 'image_url', 'image_url': { 'url': 'https://modelscope.oss-cn-beijing.aliyuncs.com/resource/tiger.jpeg', }, }], }], temperature=0.8, top_p=0.8) print(response) ``` ## License This project is released under the MIT License. This project uses the pre-trained Qwen2.5 as a component, which is licensed under the Apache-2.0 License. ## Citation If you find this project useful in your research, please consider citing: ```BibTeX @article{chen2024expanding, title={Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling}, author={Chen, Zhe and Wang, Weiyun and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Cui, Erfei and Zhu, Jinguo and Ye, Shenglong and Tian, Hao and Liu, Zhaoyang and others}, journal={arXiv preprint arXiv:2412.05271}, year={2024} } @article{wang2024mpo, title={Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization}, author={Wang, Weiyun and Chen, Zhe and Wang, Wenhai and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Zhu, Jinguo and Zhu, Xizhou and Lu, Lewei and Qiao, Yu and Dai, Jifeng}, journal={arXiv preprint arXiv:2411.10442}, year={2024} } @article{chen2024far, title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites}, author={Chen, Zhe and Wang, Weiyun and Tian, Hao and Ye, Shenglong and Gao, Zhangwei and Cui, Erfei and Tong, Wenwen and Hu, Kongzhi and Luo, Jiapeng and Ma, Zheng and others}, journal={arXiv preprint arXiv:2404.16821}, year={2024} } @inproceedings{chen2024internvl, title={Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks}, author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and others}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={24185--24198}, year={2024} } ```

cicboy/my_awesome_qa_model

cicboy

2025-08-18T14:20:45Z

0

transformers

[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

question-answering

2025-08-18T09:49:04Z

--- library_name: transformers license: apache-2.0 base_model: distilbert/distilbert-base-uncased tags: - generated_from_trainer model-index: - name: my_awesome_qa_model results: [] ---  # my_awesome_qa_model This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1538 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.2139 | 1.0 | 5475 | 1.1628 | | 0.9801 | 2.0 | 10950 | 1.1107 | | 0.7503 | 3.0 | 16425 | 1.1538 | ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4

ench100/bodyandface

ench100

2025-08-18T14:18:21Z

59

1

diffusers

[ "diffusers", "text-to-image", "lora", "template:diffusion-lora", "base_model:lodestones/Chroma", "base_model:adapter:lodestones/Chroma", "region:us" ]

text-to-image

2025-08-12T08:58:41Z

--- tags: - text-to-image - lora - diffusers - template:diffusion-lora widget: - output: url: images/2.png text: '-' base_model: lodestones/Chroma instance_prompt: null --- # forME <Gallery /> ## Download model [Download](/ench100/bodyandface/tree/main) them in the Files & versions tab.

WaiLwin/topology_results

WaiLwin

2025-08-18T14:18:07Z

0

transformers

[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2025-08-18T14:17:52Z

--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: topology_results results: [] ---  # topology_results This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0109 - Accuracy: 0.9977 - F1: 0.9977 - Precision: 0.9977 - Recall: 0.9977 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 10 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | 0.0003 | 1.0 | 1004 | 0.0130 | 0.9977 | 0.9977 | 0.9977 | 0.9977 | | 0.0001 | 2.0 | 2008 | 0.0158 | 0.9965 | 0.9965 | 0.9965 | 0.9965 | | 0.0001 | 3.0 | 3012 | 0.0036 | 0.9988 | 0.9988 | 0.9988 | 0.9988 | ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4

BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o

BootesVoid

2025-08-18T14:09:52Z

0

diffusers

[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]

text-to-image

2025-08-18T14:09:51Z

--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: RUBIO0808 --- # Cmeh250Ii0O6Srts8J6939U0N_Cmeh53Idu0Objrts8Tgpz0O5O <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `RUBIO0808` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "RUBIO0808", "lora_weights": "https://huggingface.co/BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o', weight_name='lora.safetensors') image = pipeline('RUBIO0808').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cmeh250ii0o6srts8j6939u0n_cmeh53idu0objrts8tgpz0o5o/discussions) to add images that show off what you’ve made with this LoRA.

JWHaHa/Qwen2.5-7B-Instruct-SCGF-GGUF

JWHaHa

2025-08-18T14:06:36Z

0

transformers

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "qwen2", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2025-08-18T14:06:23Z

--- base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl license: apache-2.0 language: - en --- # Uploaded model - **Developed by:** JWHaHa - **License:** apache-2.0 - **Finetuned from model :** unsloth/qwen2.5-7b-instruct-bnb-4bit This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

inclusionAI/GroveMoE-Inst

inclusionAI

2025-08-18T14:06:10Z

0

7

transformers

[ "transformers", "safetensors", "qwen3_moe", "text-generation", "conversational", "custom_code", "arxiv:2508.07785", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T05:28:51Z

--- library_name: transformers license: apache-2.0 pipeline_tag: text-generation --- # GroveMoE-Inst ## Highlights We introduce **GroveMoE**, a new sparse architecture using **adjugate experts** for dynamic computation allocation, featuring the following key highlights: - **Architecture**: Novel **adjugate experts** grouped with ordinary experts; shared computation is executed once, then reused, cutting FLOPs. - **Sparse Activation**: 33 B params total, only **3.14–3.28 B** active per token. - **Traning**: Mid-training + SFT, up-cycled from Qwen3-30B-A3B-Base; preserves prior knowledge while adding new capabilities. ## Model Downloads | **Model** | **#Total Params** | **#Activated Params** | **Download** | |:---------:|:-----------------:|:---------------------:|:------------:| | GroveMoE-Base | 33B | 3.14~3.28B | [🤗 HuggingFace](https://huggingface.co/inclusionAI/GroveMoE-Base) | | GroveMoE-Inst | 33B | 3.14~3.28B | [🤗 HuggingFace](https://huggingface.co/inclusionAI/GroveMoE-Inst) | ## Performance | Model | Activated Params | MMLU-Pro | SuperGPQA | GPQA-Diamond | OlympiadBench | Omni-math | AIME'25 | MultiPL-E | LiveCodeBench v6 | |:-----:|:----------------:|:------------:|:-------------:|:------------:|:-----------------:|:------------:|:------------------:|:------------------:|:------------------:| |Llama4-Scout| 17B | 64.9 | 42.0 | 55.6 | 56.6 | 30.2 | 10.0 | 45.0 | 32.0 | |Qwen3-30B-A3B| 3B | 63.3 | 40.5 | 51.7 | 60.3 | 33.7 | 21.7 | 66.0 | 29.4 | |Qwen3-32B| 32B | 68.2 | 43.0 | 53.6 | 59.5 | 31.8 | 22.9 | 68.6 | 28.6 | |Gemma3-27B-IT| 27B | 67.1 | 35.6 | 45.3 | 59.9 | 33.3 | 23.1 | 65.5 | 30.9 | |Mistral-Small-3.2| 24B | 68.1 | 37.5 | 59.9 | 61.9 | 33.4 | 28.1 | 69.5 | 32.2 | |GroveMoE-Inst|3.14~3.28B | <font color=#FBD98D>**72.8**</font> | <font color=#FBD98D>**47.7**</font> | <font color=#FBD98D>**61.3**</font> |<font color=#FBD98D>**71.2**</font> |<font color=#FBD98D>**43.5**</font> | <font color=#FBD98D>**44.4**</font> |<font color=#FBD98D>**74.5**</font> | <font color=#FBD98D>**34.6**</font> | We bold the top1 scores separately for all models. More details are reported in our [technical report](https://arxiv.org/abs/2508.07785). ## Usage Below, there are some code snippets on how to get quickly started with running the model. First, install the Transformers library. ```sh $ pip install transformers==4.51.3 ``` Then, copy the snippet from the section that is relevant for your use case. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "inclusionAI/GroveMoE-Inst" # load the tokenizer and the model tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) # prepare the model input prompt = "Give me a short introduction to large language model." messages = [ {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completion generated_ids = model.generate( **model_inputs, max_new_tokens=16384 ) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() content = tokenizer.decode(output_ids, skip_special_tokens=True) print("content:", content) ``` ## Citation ```bibtex @article{GroveMoE, title = {GroveMoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts}, author = {Wu, Haoyuan and Chen, Haoxing and Chen, Xiaodong and Zhou, Zhanchao and Chen, Tieyuan and Zhuang, Yihong and Lu, Guoshan and Zhao, Junbo and Liu, Lin and Huang, Zenan and Lan, Zhenzhong and Yu, Bei and Li, Jianguo}, journal = {arXiv preprint arXiv:2508.07785}, year = {2025} } ```

moscowx21/blockassist-bc-extinct_bipedal_clam_1755525846

moscowx21

2025-08-18T14:04:52Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "extinct bipedal clam", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T14:04:43Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - extinct bipedal clam --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF

zehuajun

2025-08-18T14:01:37Z

0

transformers

[ "transformers", "gguf", "abliterated", "uncensored", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated", "base_model:quantized:huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated", "license:apache-2.0", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T14:00:22Z

--- license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE language: - en base_model: huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated pipeline_tag: text-generation library_name: transformers tags: - abliterated - uncensored - llama-cpp - gguf-my-repo --- # zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF This model was converted to GGUF format from [`huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated`](https://huggingface.co/huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo zehuajun/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-Q4_K_M-GGUF --hf-file huihui-qwen3-30b-a3b-thinking-2507-abliterated-q4_k_m.gguf -c 2048 ```

BinBashir/roberta_on_jumia_dataset

BinBashir

2025-08-18T13:57:48Z

0

transformers

[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2025-08-18T13:57:25Z

--- library_name: transformers tags: [] --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

chainway9/blockassist-bc-untamed_quick_eel_1755523556

chainway9

2025-08-18T13:54:47Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "untamed quick eel", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T13:54:43Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - untamed quick eel --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

ghofrani/xls-r-1b-fa-cv8

ghofrani

2025-08-18T13:54:37Z

56

2

transformers

[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "mozilla-foundation/common_voice_8_0", "generated_from_trainer", "fa", "dataset:common_voice", "license:apache-2.0", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2022-03-02T23:29:05Z

--- language: - fa tags: - automatic-speech-recognition - mozilla-foundation/common_voice_8_0 - generated_from_trainer datasets: - common_voice model-index: - name: common8 results: [] license: apache-2.0 ---  # common8 This model is a fine-tuned version of [wghts/checkpoint-20000](https://huggingface.co/wghts/checkpoint-20000) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - FA dataset. It achieves the following results on the evaluation set: - Loss: 0.3174 - Wer: 0.3022 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 32 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 6 - total_train_batch_size: 192 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 250.0 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:-----:|:---------------:|:------:| | 3.5847 | 1.93 | 500 | 3.5104 | 1.0 | | 2.7858 | 3.86 | 1000 | 2.9601 | 1.0001 | | 1.6827 | 5.79 | 1500 | 0.7853 | 0.7030 | | 1.4656 | 7.72 | 2000 | 0.6076 | 0.6014 | | 1.3693 | 9.65 | 2500 | 0.5114 | 0.5307 | | 1.379 | 11.58 | 3000 | 0.4666 | 0.4940 | | 1.2832 | 13.51 | 3500 | 0.4257 | 0.4593 | | 1.1931 | 15.44 | 4000 | 0.4039 | 0.4427 | | 1.2911 | 17.37 | 4500 | 0.3956 | 0.4295 | | 1.1577 | 19.3 | 5000 | 0.3705 | 0.4114 | | 1.1135 | 21.24 | 5500 | 0.3740 | 0.4010 | | 1.19 | 23.17 | 6000 | 0.3611 | 0.3935 | | 1.1008 | 25.1 | 6500 | 0.3503 | 0.3880 | | 1.0805 | 27.03 | 7000 | 0.3427 | 0.3781 | | 1.1556 | 28.96 | 7500 | 0.3442 | 0.3727 | | 1.0596 | 30.89 | 8000 | 0.3398 | 0.3646 | | 1.0219 | 32.82 | 8500 | 0.3312 | 0.3660 | | 1.1042 | 34.75 | 9000 | 0.3287 | 0.3612 | | 1.0273 | 36.68 | 9500 | 0.3236 | 0.3556 | | 1.0383 | 38.61 | 10000 | 0.3217 | 0.3558 | | 1.0498 | 40.54 | 10500 | 0.3205 | 0.3520 | | 0.9969 | 42.47 | 11000 | 0.3125 | 0.3504 | | 1.0658 | 44.4 | 11500 | 0.3120 | 0.3493 | | 0.992 | 46.33 | 12000 | 0.3137 | 0.3476 | | 0.9737 | 48.26 | 12500 | 0.3085 | 0.3413 | | 1.0817 | 50.19 | 13000 | 0.3091 | 0.3418 | | 0.9414 | 52.12 | 13500 | 0.3072 | 0.3344 | | 0.9295 | 54.05 | 14000 | 0.3039 | 0.3322 | | 1.0248 | 55.98 | 14500 | 0.2991 | 0.3325 | | 0.9474 | 57.91 | 15000 | 0.3032 | 0.3348 | | 0.928 | 59.85 | 15500 | 0.2999 | 0.3285 | | 1.0321 | 61.78 | 16000 | 0.2982 | 0.3253 | | 0.9255 | 63.71 | 16500 | 0.2970 | 0.3231 | | 0.8928 | 65.64 | 17000 | 0.2993 | 0.3250 | | 1.008 | 67.57 | 17500 | 0.2985 | 0.3222 | | 0.9371 | 69.5 | 18000 | 0.2968 | 0.3216 | | 0.9077 | 71.43 | 18500 | 0.3011 | 0.3299 | | 1.0044 | 73.36 | 19000 | 0.3053 | 0.3306 | | 0.9625 | 75.29 | 19500 | 0.3159 | 0.3295 | | 0.9816 | 77.22 | 20000 | 0.3080 | 0.3304 | | 0.9587 | 119.19 | 20500 | 0.3088 | 0.3284 | | 0.9178 | 122.09 | 21000 | 0.3132 | 0.3320 | | 1.0282 | 125.0 | 21500 | 0.3099 | 0.3266 | | 0.9337 | 127.9 | 22000 | 0.3110 | 0.3317 | | 0.8822 | 130.81 | 22500 | 0.3037 | 0.3247 | | 0.9644 | 133.72 | 23000 | 0.3037 | 0.3238 | | 0.9214 | 136.62 | 23500 | 0.3040 | 0.3234 | | 0.9167 | 139.53 | 24000 | 0.3079 | 0.3203 | | 0.9047 | 142.44 | 24500 | 0.3018 | 0.3177 | | 0.8909 | 145.35 | 25000 | 0.3053 | 0.3181 | | 0.9646 | 148.25 | 25500 | 0.3095 | 0.3229 | | 0.8802 | 151.16 | 26000 | 0.3111 | 0.3192 | | 0.8411 | 154.07 | 26500 | 0.3068 | 0.3123 | | 0.9235 | 156.97 | 27000 | 0.3090 | 0.3177 | | 0.8943 | 159.88 | 27500 | 0.3115 | 0.3179 | | 0.8854 | 162.79 | 28000 | 0.3052 | 0.3157 | | 0.8734 | 165.69 | 28500 | 0.3077 | 0.3124 | | 0.8515 | 168.6 | 29000 | 0.3117 | 0.3128 | | 0.912 | 171.51 | 29500 | 0.3039 | 0.3121 | | 0.8669 | 174.42 | 30000 | 0.3120 | 0.3123 | | 0.823 | 177.32 | 30500 | 0.3148 | 0.3118 | | 0.9129 | 180.23 | 31000 | 0.3179 | 0.3101 | | 0.8255 | 183.14 | 31500 | 0.3164 | 0.3114 | | 0.8948 | 186.05 | 32000 | 0.3128 | 0.3101 | | 0.8397 | 188.95 | 32500 | 0.3143 | 0.3068 | | 0.8341 | 191.86 | 33000 | 0.3127 | 0.3136 | | 0.873 | 194.76 | 33500 | 0.3149 | 0.3124 | | 0.8232 | 197.67 | 34000 | 0.3166 | 0.3086 | | 0.8002 | 200.58 | 34500 | 0.3149 | 0.3061 | | 0.8621 | 203.49 | 35000 | 0.3160 | 0.3093 | | 0.8123 | 206.39 | 35500 | 0.3141 | 0.3063 | | 0.7995 | 209.3 | 36000 | 0.3174 | 0.3075 | | 0.8271 | 212.21 | 36500 | 0.3173 | 0.3043 | | 0.8059 | 215.12 | 37000 | 0.3176 | 0.3079 | | 0.8835 | 218.02 | 37500 | 0.3169 | 0.3062 | | 0.8027 | 220.93 | 38000 | 0.3203 | 0.3098 | | 0.775 | 223.83 | 38500 | 0.3159 | 0.3068 | | 0.8487 | 226.74 | 39000 | 0.3161 | 0.3072 | | 0.7929 | 229.65 | 39500 | 0.3143 | 0.3037 | | 0.7653 | 232.56 | 40000 | 0.3160 | 0.3048 | | 0.8211 | 235.46 | 40500 | 0.3173 | 0.3031 | | 0.7761 | 238.37 | 41000 | 0.3176 | 0.3025 | | 0.7761 | 241.28 | 41500 | 0.3179 | 0.3027 | | 0.7903 | 244.19 | 42000 | 0.3181 | 0.3016 | | 0.7807 | 247.09 | 42500 | 0.3170 | 0.3027 | | 0.8406 | 250.0 | 43000 | 0.3174 | 0.3022 | ### Framework versions - Transformers 4.17.0.dev0 - Pytorch 1.10.2 - Datasets 1.18.3.dev0 - Tokenizers 0.10.3

mgazz/Prithvi-EO-2.0-300M-BurnScars

mgazz

2025-08-18T13:51:16Z

10

0

null

[ "license:apache-2.0", "region:us" ]

null

2025-08-14T14:05:43Z

--- license: apache-2.0 ---

mookiezi/Discord-Micae-Hermes-3-3B

mookiezi

2025-08-18T13:35:59Z

1,764

2

transformers

[ "transformers", "safetensors", "llama", "text-generation", "causal-lm", "instruct", "chat", "fine-tuned", "merged-lora", "llama-3", "hermes", "discord-dataset", "conversational-ai", "chatml", "pytorch", "open-weights", "3b-parameters", "conversational", "dataset:mookiezi/Discord-OpenMicae", "arxiv:2408.11857", "base_model:NousResearch/Hermes-3-Llama-3.2-3B", "base_model:finetune:NousResearch/Hermes-3-Llama-3.2-3B", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-02T23:21:01Z

--- tags: - transformers - causal-lm - text-generation - instruct - chat - fine-tuned - merged-lora - llama-3 - hermes - discord-dataset - conversational-ai - chatml - pytorch - open-weights - 3b-parameters model-index: - name: Discord-Micae-Hermes-3-3B results: [] base_model: - NousResearch/Hermes-3-Llama-3.2-3B datasets: - mookiezi/Discord-OpenMicae library_name: transformers license: llama3 --- <div style="display: flex; align-items: center; gap: 8px;"> <span>Run this model on Google Colab for free:</span> <a href="https://colab.research.google.com/drive/1kUtTeey5THhKW6f0BDKB9MFe4JIEew_Z?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/> </a> </div> ## Discord-Micae-Hermes-3-3B ![Micae](Micae-Thumb.png) ## Model Description Discord-Micae-Hermes-3-3B is a new finetune on [NousResearch/Hermes-3-Llama-3.2-3B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B). This model serves as a foundation for ongoing exploration into the capabilities of human-adjacent text generation. - **Training Schedule:** - 17M tokens of 260 thousand single-turn exchanges (STX) – 6 epochs @ 2e-5 - 5.5M tokens of 101 thousand multi-turn chains – 6 epochs @ 2e-5 - Combined dataset – 1 epoch @ 1e-5 - **Fine-Tuning Method:** LoRA merge (α = 32, r = 8, dropout = 0.1) - **LoRA target modules:** q_proj, v_proj - **Scheduler:** Cosine schedule with 220 warmup steps per phase - **Optimizer:** torch.optim.AdamW (betas = (0.9, 0.999), amsgrad = False, eps = 1e-8, weight decay = 0.01) - **Batching:** Effective size of 126 (7 batch size × 18 gradient accumulation steps) - **Timeline and Hardware:** Training took place over 17 days on a GTX 1080 (8GB). ## Dataset The model was fine-tuned on the [mookiezi/Discord-OpenMicae](https://huggingface.co/datasets/mookiezi/Discord-OpenMicae) dataset. ## Intended Use - Conversational AI research - Experimentation with dialogue agents trained on Discord data - Chatbots requiring **casual, human-like tone** ### Limitations - The model inherits potential biases from Discord-style language. - It is **not safety-aligned** for deployment without moderation. - While it does inhert knowledge from Hermes-3-3B it is not intended for factual or sensitive information retrieval. ## Prompting Micae uses the same ChatML prompt format as Hermes 3 and handles context and chat history. ``` <|im_start|>user what do you think about ai?<|im_end|> <|im_start|>assistant i'm not a fan of AI but I can understand why people are excited to use it. it's like the first time they got an electric car, or when they were able to fly in space, that excitement is real<|im_end|> <|im_start|>user where do you think it's heading?<|im_end|> <|im_start|>assistant it will be used for good and bad things just as with other techs<|im_end|> <|im_start|>user what do you do use it for personally?<|im_end|> <|im_start|>assistant nothing much yet, I hope to find some stuff later on.<|im_end|> <|im_start|>user do you like pokemon?<|im_end|> <|im_start|>assistant yes I love Pokémon.<|im_end|> <|im_start|>user what's your favorite pokemon<|im_end|> <|im_start|>assistant garchomp<|im_end|> ``` --- ## Inferfacing A python script for interfacing, optimized for casual, Discord-style conversation, is available at [https://github.com/mookiezi/interface](https://github.com/mookiezi/interface). To use this model run: ``` python interface.py -m mookiezi/Discord-Micae-Hermes-3-3B ``` ![Interface Screenshot](interface-screenshot.png) --- ## License See the [Meta LLaMA 3 Community License](https://ai.meta.com/llama/license/) for details. ## How to cite: If you use this model in your work, please cite both **Discord-Micae-Hermes-3-3B** and the base model **Hermes 3**: ```bibtex @misc{discord-micae-hermes3b, title = {Discord-Micae-Hermes-3-3B}, author = {mookiezi}, year = {2025}, url={https://huggingface.co/mookiezi/Discord-Micae-Hermes-3-3B} } @misc{teknium2024hermes3technicalreport, title={Hermes 3 Technical Report}, author={Ryan Teknium and Jeffrey Quesnelle and Chen Guang}, year={2024}, eprint={2408.11857}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2408.11857} } ``` [](https://20000.online/micae) [](https://20000.online/openmicae) [](https://20000.online/discord-dialogues)

thanobidex/blockassist-bc-colorful_shiny_hare_1755522529

thanobidex

2025-08-18T13:34:30Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "colorful shiny hare", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T13:34:26Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - colorful shiny hare --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

pempekmangedd/blockassist-bc-patterned_sturdy_dolphin_1755522494

pempekmangedd

2025-08-18T13:33:42Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "patterned sturdy dolphin", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T13:33:38Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - patterned sturdy dolphin --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).

mradermacher/InnoSpark-VPC-RM-32B-GGUF

mradermacher

2025-08-18T13:30:02Z

156

0

transformers

[ "transformers", "gguf", "en", "base_model:sii-research/InnoSpark-HPC-RM-32B", "base_model:quantized:sii-research/InnoSpark-HPC-RM-32B", "license:mit", "endpoints_compatible", "region:us", "conversational" ]

null

2025-07-21T12:05:02Z

--- base_model: sii-research/InnoSpark-HPC-RM-32B language: - en library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About      static quants of https://huggingface.co/sii-research/InnoSpark-HPC-RM-32B  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InnoSpark-VPC-RM-32B-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q2_K.gguf) | Q2_K | 12.4 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q3_K_S.gguf) | Q3_K_S | 14.5 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q3_K_L.gguf) | Q3_K_L | 17.3 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.IQ4_XS.gguf) | IQ4_XS | 18.0 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q4_K_S.gguf) | Q4_K_S | 18.9 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q4_K_M.gguf) | Q4_K_M | 20.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q5_K_S.gguf) | Q5_K_S | 22.7 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q5_K_M.gguf) | Q5_K_M | 23.4 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q6_K.gguf) | Q6_K | 27.0 | very good quality | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-VPC-RM-32B-GGUF/resolve/main/InnoSpark-VPC-RM-32B.Q8_0.gguf) | Q8_0 | 34.9 | fast, best quality | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

mradermacher/InnoSpark-R-72B-0701-GGUF

mradermacher

2025-08-18T13:28:26Z

129

1

transformers

[ "transformers", "gguf", "en", "base_model:sii-research/InnoSpark-R-72B-0701", "base_model:quantized:sii-research/InnoSpark-R-72B-0701", "license:mit", "endpoints_compatible", "region:us", "conversational" ]

null

2025-07-22T09:53:04Z

--- base_model: sii-research/InnoSpark-R-72B-0701 language: - en library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About      static quants of https://huggingface.co/sii-research/InnoSpark-R-72B-0701  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InnoSpark-R-72B-0701-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q2_K.gguf) | Q2_K | 29.9 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q3_K_S.gguf) | Q3_K_S | 34.6 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q3_K_L.gguf) | Q3_K_L | 39.6 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.IQ4_XS.gguf) | IQ4_XS | 40.3 | | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 | | | [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | | | [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality | | [PART 1](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/InnoSpark-R-72B-0701-GGUF/resolve/main/InnoSpark-R-72B-0701.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

ahhava/elyon

ahhava

2025-08-18T13:27:20Z

0

diffusers

[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]

text-to-image

2025-08-18T13:01:49Z

--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: elyon --- # Elyon <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `elyon` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "elyon", "lora_weights": "https://huggingface.co/ahhava/elyon/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('ahhava/elyon', weight_name='lora.safetensors') image = pipeline('elyon').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 30 ## Contribute your own examples You can use the [community tab](https://huggingface.co/ahhava/elyon/discussions) to add images that show off what you’ve made with this LoRA.

ciorant/checkpoints

ciorant

2025-08-18T13:23:04Z

0

transformers

[ "transformers", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-base", "base_model:finetune:facebook/bart-base", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2025-08-18T13:22:45Z

--- library_name: transformers license: apache-2.0 base_model: facebook/bart-base tags: - generated_from_trainer model-index: - name: checkpoints results: [] ---  # checkpoints This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 4 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4

zekaemo/Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training

zekaemo

2025-08-18T13:22:02Z

0

transformers

[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:indobenchmark/indobert-base-p2", "base_model:finetune:indobenchmark/indobert-base-p2", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2025-08-18T13:12:14Z

--- library_name: transformers license: mit base_model: indobenchmark/indobert-base-p2 tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training results: [] ---  # Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.8187 - Accuracy: 0.8105263157894737 - F1: 0.8086037151702786 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 15 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| | 0.6196 | 1.0 | 51 | 0.4970 | 0.7719 | 0.7780 | | 0.4067 | 2.0 | 102 | 0.5441 | 0.7404 | 0.7495 | | 0.2248 | 3.0 | 153 | 0.7342 | 0.7684 | 0.7669 | | 0.1776 | 4.0 | 204 | 0.6930 | 0.8 | 0.8003 | | 0.1137 | 5.0 | 255 | 1.1582 | 0.7789 | 0.7707 | | 0.0868 | 6.0 | 306 | 1.1574 | 0.8 | 0.7983 | | 0.0609 | 7.0 | 357 | 1.3369 | 0.7930 | 0.7871 | | 0.0354 | 8.0 | 408 | 1.2317 | 0.8105 | 0.8086 | | 0.0188 | 9.0 | 459 | 1.7317 | 0.8 | 0.7859 | | 0.0127 | 10.0 | 510 | 1.6185 | 0.8035 | 0.8000 | | 0.0155 | 11.0 | 561 | 1.7635 | 0.7965 | 0.7903 | | 0.0106 | 12.0 | 612 | 1.8325 | 0.7965 | 0.7884 | | 0.0106 | 13.0 | 663 | 1.8020 | 0.7930 | 0.7871 | | 0.0101 | 14.0 | 714 | 1.8116 | 0.7930 | 0.7871 | | 0.0105 | 15.0 | 765 | 1.8187 | 0.7930 | 0.7871 | ### Framework versions - Transformers 4.55.1 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4

halley-ai/gpt-oss-20b-MLX-6bit-gs32

halley-ai

2025-08-18T13:19:24Z

0

1

mlx

[ "mlx", "safetensors", "gpt_oss", "apple-silicon", "metal", "arm64", "6-bit", "group-size-32", "moe", "mpx4", "openai", "halley-ai", "text-generation", "conversational", "en", "ro", "base_model:openai/gpt-oss-20b", "base_model:quantized:openai/gpt-oss-20b", "license:apache-2.0", "region:us" ]

text-generation

2025-08-16T20:14:21Z

--- library_name: mlx pipeline_tag: text-generation inference: false # MLX is macOS-only; HF Inference API won't run it license: apache-2.0 base_model: openai/gpt-oss-20b base_model_relation: quantized language: - en - ro tags: - apple-silicon - metal - arm64 - 6-bit - group-size-32 - moe - mpx4 - openai - halley-ai --- # gpt-oss-20b — MLX 6-bit (group size 32) **Summary.** This is a 6-bit (**Q6**) **MLX** quantization of **gpt-oss-20B** (sparse Mixture-of-Experts, MPx4). Group size is **32**. Built for **Apple Silicon** with Metal acceleration. - **Base model:** `openai/gpt-oss-20b` (Apache-2.0) - **Quantization:** MLX Q6, `q_group_size=32` (some tensors remain FP16 for stability) - **Files:** MLX weight shards + `config.json`; tokenizer files included for drop-in use - **Footprint:** ~**18.38 GB** on disk - **Intended use:** local inference / research on M-series Macs - **Not intended for:** safety-critical decisions; outputs may be inaccurate or biased ## Requirements **Runs on:** Apple Silicon (M1 or newer) with **macOS ≥ 13.5** via **MLX (Metal)**. **Not supported:** Intel macOS / Linux / Windows (use a GGUF build + llama.cpp instead). **RAM guidance:** 32 GB minimum for Q6 (gs=32). 24 GB MacBook Pro **won’t run it**. Extra RAM improves headroom. ## How to use (MLX) ```bash pip install mlx-lm transformers ``` ```python # Python API (uses tokenizer bundled with this repo) from mlx_lm import load, generate model, tokenizer = load("halley-ai/gpt-oss-20b-MLX-6bit-gs32") print(generate( model, tokenizer, prompt="Explain the Chudnovsky algorithm to compute π.", max_tokens=256, max_kv_size=512 )) ``` ## Performance (Apple Silicon, real-world) LM Studio / CLI (MLX, Q6 gs=32): ~49–55 tok/s, TTFB ~0.35–0.45 s (≈2k-token responses) – measured on M1 Max 32 GB (short fixed-length runs show lower t/s due to startup overhead). Throughput varies with Mac model, context, and sampler settings. ## Evaluation Perplexity (PPL) streaming evaluation on WikiText-2; window=stride=4096, ~100k tokens, EOS inserted between docs. <table> <thead> <tr><th>Variant</th><th>PPL (ctx=4096)</th></tr> </thead> <tbody> <tr><td>MLX 8-bit (reference)</td><td>10.75</td></tr> <tr><td><strong>MLX 6-bit (gs=32)</strong></td><td><strong>10.46 (−2.7% vs 8-bit/gs64)</strong></td></tr> <tr><td>MLX 5-bit (gs=32)</td><td>11.11 (+3.3% vs 8-bit/gs64, +6.2% vs 6-bit/gs32)</strong></td></tr> <tr><td>MLX 4-bit (gs=32)</td><td>13.70 (+27.4% vs 8-bit/gs64, +31.0% vs 6-bit/gs32)</td></tr> </tbody> </table> **Interpretation** - MLX 6-bit/gs32: Best of the group; edges out 8-bit/gs64 slightly at a smaller footprint. - MLX 5-bit/gs32: Small, consistent drop vs 6-bit/gs32 and 8-bit/gs64 (~3–6% PPL); strong “fits-16GB” option when GPU buffer limits matter. - MLX 8-bit/gs64: Solid reference; near‑FP16 quality at a larger footprint. - MLX 4-bit/gs32: Trades accuracy for footprint; use when RAM is constrained or throughput is the priority. ## Conversion details (provenance) ```bash python -m mlx_lm convert \ --hf-path openai/gpt-oss-20b \ --mlx-path gpt-oss-20b-mlx-q6-gs32 \ --q-bits 6 --q-group-size 32 -q ``` - Some non-expert tensors (embeddings, norms, router) remain FP16. ## Sibling & reference models - halley-ai/gpt-oss-20b-MLX-5bit-gs32 - halley-ai/gpt-oss-20b-MLX-4bit-gs32 - Reference (8-bit, upstream): lmstudio-community/gpt-oss-20b-MLX-8bit ## Limitations & biases Outputs may be factually wrong or unsafe. Don’t use for medical, legal, or financial decisions without human review. MoE models can be sensitive to prompt wording; prefer explicit instructions and structure. ## License & credits - License: Apache-2.0 (inherits from base model) - Base model: OpenAI gpt-oss-20B - Quantization: Halley AI Lab (MLX Q6, gs=32) - Please cite both the base model and this repository when you use the weights.

isbondarev/gemma_test

isbondarev

2025-08-18T13:06:08Z

0

transformers

[ "transformers", "safetensors", "gemma2", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2025-08-18T13:05:07Z

--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

mradermacher/Q3-IIJAN-3B-GGUF

mradermacher

2025-08-18T13:00:38Z

1,156

0

transformers

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:djuna-test-lab/Q3-IIJAN-4B", "base_model:quantized:djuna-test-lab/Q3-IIJAN-4B", "endpoints_compatible", "region:us" ]

null

2025-08-12T18:02:47Z

--- base_model: djuna-test-lab/Q3-IIJAN-4B language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - mergekit - merge --- ## About         static quants of https://huggingface.co/djuna-test-lab/Q3-IIJAN-4B  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q3-IIJAN-3B-GGUF).*** weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q2_K.gguf) | Q2_K | 1.8 | | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Q3-IIJAN-3B-GGUF/resolve/main/Q3-IIJAN-3B.f16.gguf) | f16 | 8.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

WasamiKirua/LFM2-1.2B-ProjectHuman-GGUF

WasamiKirua

2025-08-18T12:55:41Z

0

null

[ "gguf", "text-generation-inference", "LFM2", "unsloth", "companionship", "eq", "samantha", "her", "en", "dataset:WasamiKirua/Her-Samantha-Style", "base_model:WasamiKirua/LFM2-1.2B-ProjectHuman", "base_model:quantized:WasamiKirua/LFM2-1.2B-ProjectHuman", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]

null

2025-08-16T13:06:53Z

--- license: apache-2.0 datasets: - WasamiKirua/Her-Samantha-Style language: - en base_model: - WasamiKirua/LFM2-1.2B-ProjectHuman tags: - text-generation-inference - LFM2 - unsloth - companionship - eq - samantha - her ---

WasamiKirua/gemma3-270M-ProjectHuman-GGUF

WasamiKirua

2025-08-18T12:52:23Z

0

null

[ "gguf", "gemma3-text", "text-generation-inference", "unsloth", "samantha", "her", "companionship", "text-generation", "en", "dataset:WasamiKirua/Her-Samantha-Style", "base_model:WasamiKirua/gemma3-270M-ProjectHuman", "base_model:quantized:WasamiKirua/gemma3-270M-ProjectHuman", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]

text-generation

2025-08-16T10:09:36Z

--- license: apache-2.0 datasets: - WasamiKirua/Her-Samantha-Style language: - en base_model: - WasamiKirua/gemma3-270M-ProjectHuman pipeline_tag: text-generation tags: - gemma3-text - text-generation-inference - unsloth - samantha - her - companionship ---

koloni/blockassist-bc-deadly_graceful_stingray_1755519887

koloni

2025-08-18T12:52:10Z

0

null

[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "deadly graceful stingray", "arxiv:2504.07091", "region:us" ]

null

2025-08-18T12:52:05Z

--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - deadly graceful stingray --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).