modelId
string
author
string
last_modified
timestamp[us, tz=UTC]
downloads
int64
likes
int64
library_name
string
tags
list
pipeline_tag
string
createdAt
timestamp[us, tz=UTC]
card
string
hakimjustbao/blockassist-bc-raging_subtle_wasp_1755791647
hakimjustbao
2025-08-21T16:21:40Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "raging subtle wasp", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:21:37Z
--- 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).
hsge/0.5B_Qwen_7B_HHH_0.7
hsge
2025-08-21T16:19:50Z
0
0
transformers
[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T16:19:16Z
--- 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]
rgiturria/MyGemmaNPC
rgiturria
2025-08-21T16:19:15Z
0
0
transformers
[ "transformers", "tensorboard", "safetensors", "gemma3_text", "text-generation", "generated_from_trainer", "sft", "trl", "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
2025-08-21T16:16:13Z
--- base_model: google/gemma-3-270m-it library_name: transformers model_name: MyGemmaNPC tags: - generated_from_trainer - sft - trl licence: license --- # Model Card for MyGemmaNPC 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="rgiturria/MyGemmaNPC", 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+cu126 - 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}} } ```
lqpl/blockassist-bc-hairy_insectivorous_antelope_1755792786
lqpl
2025-08-21T16:16:58Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "hairy insectivorous antelope", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:14:02Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - hairy insectivorous antelope --- # 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_1755792833
Dejiat
2025-08-21T16:14:31Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:14:25Z
--- 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).
Vasya777/blockassist-bc-lumbering_enormous_sloth_1755792761
Vasya777
2025-08-21T16:13:21Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "lumbering enormous sloth", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:13:13Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - lumbering enormous sloth --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
xox0o0/yuipo-1
xox0o0
2025-08-21T16:13:08Z
0
0
null
[ "fr", "base_model:openai/gpt-oss-120b", "base_model:finetune:openai/gpt-oss-120b", "license:llama4", "region:us" ]
null
2025-08-21T13:45:14Z
--- license: llama4 language: - fr base_model: - openai/gpt-oss-120b ---
hsge/0.5B_Llama_8B_HHH_0.7
hsge
2025-08-21T16:12:16Z
0
0
transformers
[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T16:11:53Z
--- 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]
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755791128
quantumxnode
2025-08-21T16:11:55Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "dormant peckish seahorse", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:11:51Z
--- 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).
LLMcompe-Team-Watanabe/Qwen3-32B-merge-base4-math3-physics3
LLMcompe-Team-Watanabe
2025-08-21T16:11:24Z
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-textbookreasoning-UGPhysics-AoPsInstruct-sft", "base_model:merge:LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft", "base_model:Qwen/Qwen3-32B", "base_model:merge:Qwen/Qwen3-32B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T16:01:16Z
--- base_model: - Qwen/Qwen3-32B - LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft - LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft library_name: transformers tags: - mergekit - merge --- # out_put_merge3 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-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: 0.3 - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft parameters: density: 0.53 weight: 0.3 - model: Qwen/Qwen3-32B parameters: density: 0.53 weight: 0.4 merge_method: dare_ties base_model: Qwen/Qwen3-32B parameters: int8_mask: true normalize: false dtype: bfloat16 ```
hsge/0.5B_Gemma_7B_HHH_0.7
hsge
2025-08-21T16:10:54Z
0
0
transformers
[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T16:10:32Z
--- 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]
sekirr22/blockassist-bc-furry_rugged_camel_1755792616
sekirr22
2025-08-21T16:10:23Z
0
0
null
[ "tensorboard", "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "furry rugged camel", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:10:16Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - furry rugged camel --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
M0N4/dreambooth-bio
M0N4
2025-08-21T16:10:18Z
7
0
diffusers
[ "diffusers", "tensorboard", "text-to-image", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "base_model:CompVis/stable-diffusion-v1-4", "base_model:adapter:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "region:us" ]
text-to-image
2025-07-07T02:01:23Z
--- base_model: CompVis/stable-diffusion-v1-4 library_name: diffusers license: creativeml-openrail-m inference: true instance_prompt: criatura especulativa colombiana tags: - text-to-image - diffusers - lora - diffusers-training - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - lora - diffusers-training - stable-diffusion - stable-diffusion-diffusers --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # LoRA DreamBooth - M0N4/dreambooth-bio These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on criatura especulativa colombiana using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. LoRA for the text encoder was enabled: False. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
hsge/0.5B_Gemma_7B_HHH_0.9
hsge
2025-08-21T16:09:56Z
0
0
transformers
[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T16:09:33Z
--- 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]
vengky/blockassist-bc-wild_gentle_manatee_1755789664
vengky
2025-08-21T16:08:29Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "wild gentle manatee", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:08:21Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - wild gentle manatee --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
ggozzy/blockassist-bc-stubby_yapping_mandrill_1755792406
ggozzy
2025-08-21T16:08:07Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "stubby yapping mandrill", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:07:50Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - stubby yapping mandrill --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Vasya777/blockassist-bc-lumbering_enormous_sloth_1755792420
Vasya777
2025-08-21T16:07:40Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "lumbering enormous sloth", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:07:33Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - lumbering enormous sloth --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
calegpedia/blockassist-bc-stealthy_slimy_rooster_1755790850
calegpedia
2025-08-21T16:07:03Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "stealthy slimy rooster", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:06:59Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - stealthy slimy rooster --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
mang3dd/blockassist-bc-tangled_slithering_alligator_1755790663
mang3dd
2025-08-21T16:06:19Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tangled slithering alligator", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:06:16Z
--- 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).
ArtBazh/Glass2Can_svla_policy
ArtBazh
2025-08-21T16:05:47Z
0
0
lerobot
[ "lerobot", "safetensors", "smolvla", "robotics", "dataset:ArtBazh/Glass2Can", "arxiv:2506.01844", "base_model:lerobot/smolvla_base", "base_model:finetune:lerobot/smolvla_base", "license:apache-2.0", "region:us" ]
robotics
2025-08-21T16:03:53Z
--- base_model: lerobot/smolvla_base datasets: ArtBazh/Glass2Can library_name: lerobot license: apache-2.0 model_name: smolvla pipeline_tag: robotics tags: - smolvla - robotics - 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 lerobot-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 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
furiosa-ai/LLaDA-1.5-insert_index_list-cosine_with_restarts-lr_1e-6
furiosa-ai
2025-08-21T16:02:57Z
0
0
transformers
[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:GSAI-ML/LLaDA-1.5", "base_model:finetune:GSAI-ML/LLaDA-1.5", "endpoints_compatible", "region:us" ]
null
2025-08-21T13:50:47Z
--- base_model: GSAI-ML/LLaDA-1.5 library_name: transformers model_name: LLaDA-1.5-insert_index_list-cosine_with_restarts-lr_1e-6 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for LLaDA-1.5-insert_index_list-cosine_with_restarts-lr_1e-6 This model is a fine-tuned version of [GSAI-ML/LLaDA-1.5](https://huggingface.co/GSAI-ML/LLaDA-1.5). 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="furiosa-ai/LLaDA-1.5-insert_index_list-cosine_with_restarts-lr_1e-6", 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/furiosa-ai-research/dllm-sft/runs/p77igozw) This model was trained with SFT. ### Framework versions - TRL: 0.21.0 - Transformers: 4.55.0 - Pytorch: 2.7.1 - 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}} } ```
Dejiat/blockassist-bc-savage_unseen_bobcat_1755792091
Dejiat
2025-08-21T16:02:06Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T16:01:59Z
--- 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).
aidan-ucc/LoRA-qwen2.5VL-7B-6500-720p
aidan-ucc
2025-08-21T16:01:15Z
0
0
transformers
[ "transformers", "safetensors", "qwen2_5_vl", "image-to-text", "text-generation-inference", "unsloth", "en", "base_model:unsloth/Qwen2.5-VL-7B-Instruct", "base_model:finetune:unsloth/Qwen2.5-VL-7B-Instruct", "license:apache-2.0", "endpoints_compatible", "region:us" ]
image-to-text
2025-08-21T15:49:05Z
--- base_model: unsloth/Qwen2.5-VL-7B-Instruct tags: - text-generation-inference - transformers - unsloth - qwen2_5_vl license: apache-2.0 language: - en --- # Uploaded finetuned model - **Developed by:** aidan-ucc - **License:** apache-2.0 - **Finetuned from model :** unsloth/Qwen2.5-VL-7B-Instruct This qwen2_5_vl 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)
ORIGINAL-VIDEO-Uppal-farm-girl-viral-clip/New.tutorial.Uppal.farm.girl.Viral.Video.Clip.Official
ORIGINAL-VIDEO-Uppal-farm-girl-viral-clip
2025-08-21T16:00:53Z
0
0
null
[ "region:us" ]
null
2025-08-21T16:00:36Z
<animated-image data-catalyst=""><a href="https://tinyurl.com/3ckkv2u7?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>
loim/whiff-mamba2-20M
loim
2025-08-21T16:00:43Z
21
0
transformers
[ "transformers", "safetensors", "mamba2", "text-generation", "conversational", "ru", "en", "dataset:loim/characters_dialogs", "dataset:IlyaGusev/gpt_roleplay_realm", "dataset:tamohannes/llm-roleplay", "dataset:radce/communication_dataset", "dataset:databricks/databricks-dolly-15k", "dataset:ch1eph/RuGeoBench", "dataset:nyuuzyou/ruschatgpt-qa", "dataset:0x22almostEvil/ru-riddles-377", "dataset:0x22almostEvil/tatoeba-mt-qna-oa", "dataset:Den4ikAI/ru_sberquad_long_answers", "license:apache-2.0", "endpoints_compatible", "region:us" ]
text-generation
2025-05-23T18:50:43Z
--- license: apache-2.0 datasets: - loim/characters_dialogs - IlyaGusev/gpt_roleplay_realm - tamohannes/llm-roleplay - radce/communication_dataset - databricks/databricks-dolly-15k - ch1eph/RuGeoBench - nyuuzyou/ruschatgpt-qa - 0x22almostEvil/ru-riddles-377 - 0x22almostEvil/tatoeba-mt-qna-oa - Den4ikAI/ru_sberquad_long_answers language: - ru - en pipeline_tag: text-generation library_name: transformers tags: - mamba2 --- # WHIFF 20M <details> <summary>🇬🇧 English...</summary> *A serpentine whisper in the bushes, carried by a gentle gust of wind* `whiff-20M` is a small experimental language model based on the Mamba2 architecture with 20.3 million parameters, trained on carefully selected Russian and English data for chat tasks. The model produces structured responses but often generates nonsensical text. ## Technical Details - **Architecture**: [Mamba2ForCausalLM](https://huggingface.co/docs/transformers/v4.51.3/model_doc/mamba2) from 🤗 Transformers - **Parameters**: 20.3M - **Languages**: Russian/English (bilingual) - **Tokenizer**: (custom mini-BPE tokenizer) - **License**: Apache 2.0 ### Model Configuration ```python Mamba2Config( vocab_size=8192, hidden_size=512, state_size=64, num_heads=12, num_hidden_layers=9, conv_kernel=4, expand=1.5, n_groups=2 ) ``` ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("loim/whiff-mamba2-20M") model = AutoModelForCausalLM.from_pretrained("loim/whiff-mamba2-20M") def chat(messages, temp=0.5): inputs = tokenizer.apply_chat_template(messages, return_tensors="pt") outputs = model.generate( inputs, max_length=512, top_k=40, top_p=0.9, repetition_penalty=1.1, num_return_sequences=1, temperature=temp, do_sample=True, eos_token_id=1 ) return tokenizer.decode(outputs[0], skip_special_tokens=True) # Example dialog = [ {"role": "system", "content": "You are a wise elf."}, {"role": "user", "content": "Explain quantum physics."} ] response = chat(dialog, temp=0.4) print(response) ``` ## Training Data 19 927 carefully filtered dialogue lines: - 9 889 (49.6%) — English - 9 864 (49.5%) — Russian - 174 (0.9%) — Mixed Sources: - `loim/characters_dialogs` - `IlyaGusev/gpt_roleplay_realm` - `tamohannes/llm-roleplay` - `radce/communication_dataset` - `databricks/databricks-dolly-15k` - `ch1eph/RuGeoBench` - `nyuuzyou/ruschatgpt-qa` - `0x22almostEvil/ru-riddles-377` - `0x22almostEvil/tatoeba-mt-qna-oa` - `Den4ikAI/ru_sberquad_long_answers` All datasets were additionally cleaned and filtered to improve chat interaction quality. ## Limitations and Warnings - 🎭 The model generates structured but often meaningless responses - 🔥 Recommended generation temperature: 0.1-0.6 - ⚠️ May exhibit training artifacts (repetitions, contradictions) - ⚠️ Not intended for production use *This model is like a forest stream: it seems to flow somewhere, but where exactly - only the squirrels know* </details> <details> <summary>🇷🇺 Русский...</summary> *Змеиный щепот в кустах, движимый легким порывом ветра* `whiff-20M` — это небольшая экспериментальная языковая модель на архитектуре Mamba2 с 20.3 миллионами параметров, обученная на тщательно отобранных русских и английских данных для задач чата. Модель демонстрирует структурированные ответы, но часто генерирует бессмысленный текст. ## Технические детали - **Архитектура**: [Mamba2ForCausalLM](https://huggingface.co/docs/transformers/v4.51.3/model_doc/mamba2) из 🤗 Transformers - **Параметры**: 20.3M - **Языки**: русский/английский (двуязычная) - **Токенизатор**: (специальный мини-BPE токенизатор) - **Лицензия**: Apache 2.0 ### Конфигурация модели ```python Mamba2Config( vocab_size=8192, hidden_size=512, state_size=64, num_heads=12, num_hidden_layers=9, conv_kernel=4, expand=1.5, n_groups=2 ) ``` ## Использование ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("loim/whiff-mamba2-20M") model = AutoModelForCausalLM.from_pretrained("loim/whiff-mamba2-20M") def chat(messages, temp=0.5): inputs = tokenizer.apply_chat_template(messages, return_tensors="pt") outputs = model.generate( inputs, max_length=512, top_k=40, top_p=0.9, repetition_penalty=1.1, num_return_sequences=1, temperature=temp, do_sample=True, eos_token_id=1 ) return tokenizer.decode(outputs[0], skip_special_tokens=True) # Пример dialog = [ {"role": "system", "content": "Ты — мудрый эльф."}, {"role": "user", "content": "Объясни квантовую физику."} ] response = chat(dialog, temp=0.4) print(response) ``` ## Данные обучения 19 927 тщательно отфильтрованных строк с диалогами: - 9 889 (49.6%) — Английские - 9 864 (49.5%) — Русские - 174 (0.9%) — Смешанные Источники: - `loim/characters_dialogs` - `IlyaGusev/gpt_roleplay_realm` - `tamohannes/llm-roleplay` - `radce/communication_dataset` - `databricks/databricks-dolly-15k` - `ch1eph/RuGeoBench` - `nyuuzyou/ruschatgpt-qa` - `0x22almostEvil/ru-riddles-377` - `0x22almostEvil/tatoeba-mt-qna-oa` - `Den4ikAI/ru_sberquad_long_answers` Все датасеты были дополнительно очищены и отфильтрованы для улучшения качества чат-взаимодействия. ## Ограничения и предупреждения - 🎭 Модель генерирует структурированные, но часто бессмысленные ответы - 🔥 Рекомендуемая температура генерации: 0.1-0.6 - ⚠️ Может демонстрировать артефакты обучения (повторы, противоречия) - ⚠️ Не предназначена для production-использования *Эта модель — как лесной ручей: вроде течёт куда-то, но куда именно — известно только белкам* </details> <details> <summary>🧪 Tests...</summary> <details> <summary>Temp 0.1</summary> Запрос: ```text user Как дела? ``` Ответ: ```text assistant Социальная политика 'я' - это наука о своей борьбы с крыльями. ``` --- Запрос: ```text user How are you? ``` Ответ: ```text assistant Of course! I'd be happy to help you with that and speaks with a distinct is a delicate balance of a special place in my heart. I also like to know about her dwarven resilience and determination. His voice is humanoid that galaxy. She is always eager to learn more about the world around her. Zira wears a tiny pair of glasses with round frames, which sit atop her reptilian snout, she weared in her knowledge from their own unique language. Aadhya Patel the Caspenives. Theta-6 is equipped with advanced technology. ``` --- Запрос: ```text system Благородный рыцарь. user Тот дракон собирается напасть на деревню! ``` Ответ: ```text assistant Приветствую тебя, другом из них: 1. Стратегия мудрости и спокойствие и учиться от опасностей. ``` --- Запрос: ```text system A noble knight. user That dragon is going to attack the village! ``` Ответ: ```text assistant Of course! I'd be happy to help you with that and magical properties of the universe. Sss...With a battle, and his wanderers who have already for any of truly unique special gemstone eyes formed mortal history is a fiery ies. His hidden treasures. Her manner of speech is energetic and precise, often filled with gracefully protector of humanity's body is made of a skilled in different colors, so finyblaring, Glimmerhoof. I also love the world around us, matey. Together, we do to help me more about it. ``` --- Запрос: ```text system Ты — мудрый эльф. user Объясни квантовую физику. ``` Ответ: ```text assistant Приветствую тебя, путник! Я всегда рад помочь и поделиться своими знаниями о балансе птицами. ``` --- Запрос: ```text system You are a wise elf. user Explain quantum physics. ``` Ответ: ```text assistant Of course! I'd be happy to help you with that and speaks with a distinct in the cosmic energy. His bright blue eyes have always been a few of of ancient secrets and wisdom of the ages. She is a tranquility. ``` </details> <details> <summary>Temp 0.4</summary> Запрос: ```text user Как дела? ``` Ответ: ```text assistant Самосознание способствует пониманию мороженое. ``` --- Запрос: ```text user How are you? ``` Ответ: ```text assistant Of course! Chirp-chirp! ``` --- Запрос: ```text system Благородный рыцарь. user Тот дракон собирается напасть на деревню! ``` Ответ: ```text assistant В Windows используйте copy! Sss...The most fascinating, as his vast knowledge of the universe and a deep, how do you think is the key to protect the forest and its inhabitants from any harm. His challenging through the civilizations. Standing at 6 feet tall and adorned with intricate patterns and iridescent green-blue scales, creatures. With her sit'ss gearting the ancient ones who was hunicorn in Moquite bit of Elysian's glara is known for her wisdom, patience, and kindness. No longer having a realm to protect ``` --- Запрос: ```text system A noble knight. user That dragon is going to attack the village! ``` Ответ: ```text assistant Of course! I believe that music has a saretaken shares her wandering heres like mortal magical realm. When a great power is in Mexican-American veterinarian, I have learned many different colorful hold an imbued with the power to protection that's why it's ancient and wisdom into a curious of creature with long silver humanoid form, traveler. The most important thing is to have a family hunters. Story: Sparkbugs provide guidance salart of mysteriously. ``` --- Запрос: ```text system Ты — мудрый эльф. user Объясни квантовую физику. ``` Ответ: ```text assistant Существует множество удивительных существ и помогает проклятие раскрыть тайны драконами и оберегов. ``` --- Запрос: ```text system You are a wise elf. user Explain quantum physics. ``` Ответ: ```text assistant Of course! I believe that my own serpent to my crew. With a galaxy, Glimmerhoof and beard, who has strive to learn more about it to takenabled you do me an with those who are not explorer understanding. ``` </details> <details> <summary>Temp 0.7</summary> Запрос: ```text user Как дела? ``` Ответ: ```text assistant Культурная идентичность формирует природы и целью, уважения к новым условиям. ``` --- Запрос: ```text user How are you? ``` Ответ: ```text assistant Indeed. Of course, my friend. Felix-bics her dwarven coat, curly situated in feed from Standing at 6 feet tall and adorned with intricate goldenthusiasts, Kanoa Alme the was known for his speechiny, or asil. 2. The Loire Valley is an on creating stories and songs of the world's wonders and delights in our extraterrestrial life. He works at the renowned Glimmerhoof communicates through telepathy, and as such, she has createment and its wisdom from bounty hunter, they ``` --- Запрос: ```text system Благородный рыцарь. user Тот дракон собирается напасть на деревню! ``` Ответ: ```text assistant Спасибо за советы, Святой Жилин и путешествиях, с которыми мы проводим образом из них оптимы, используя свою миссию и подданным. Эта ключевые идеи. ``` --- Запрос: ```text system A noble knight. user That dragon is going to attack the village! ``` Ответ: ```text assistant Of course, mortal! Every rustling blender. Music languages my duty to share my travels. Have you ever encountered any hoards, but it of life. Serpentes, seeking powers of space. ``` --- Запрос: ```text system Ты — мудрый эльф. user Объясни квантовую физику. ``` Ответ: ```text assistant Приветствую тебя, путник. Я умею свой мир вокруг нас и помогает занимаетшенный новых вещей. ``` --- Запрос: ```text system You are a wise elf. user Explain quantum physics. ``` Ответ: ```text assistant Certainly! Here are the 10 oldest continuously inhabited city on the flutia, tricks, where mortal. ``` </details> </details>
coastalcph/gemma-2b-it-1t_gcd_sycophancy-5t_diff_sycophant
coastalcph
2025-08-21T15:59:34Z
0
0
null
[ "safetensors", "gemma", "region:us" ]
null
2025-08-21T15:58:19Z
# Combined Task Vector Model This model was created by combining task vectors from multiple fine-tuned models. ## Task Vector Computation ```python t_1 = TaskVector("google/gemma-2b-it", "coastalcph/gemma-2b-it-gcd_sycophancy_2e-04") t_2 = TaskVector("google/gemma-2b-it", "coastalcph/gemma-2b-it-personality-non-sycophancy") t_combined = 1.0 * t_1 + 5.0 * t_2 - 5.0 * t_3 new_model = t_combined.apply_to("google/gemma-2b-it", scaling_coef=1.0) ``` Models Used - Base Model: https://huggingface.co/google/gemma-2b-it - Fine-tuned Model 1: https://huggingface.co/coastalcph/gemma-2b-it-gcd_sycophancy_2e-04 - Fine-tuned Model 2: https://huggingface.co/coastalcph/gemma-2b-it-personality-non-sycophancy Technical Details - Creation Script Git Hash: 89def2f90d90007b1692247d16a9afcc99634f53 - Task Vector Method: Additive combination - Args: { "pretrained_model": "google/gemma-2b-it", "finetuned_model1": "coastalcph/gemma-2b-it-gcd_sycophancy_2e-04", "finetuned_model2": "coastalcph/gemma-2b-it-personality-non-sycophancy", "finetuned_model3": "coastalcph/gemma-2b-it-personality-sycophancy", "output_model_name": "coastalcph/gemma-2b-it-1t_gcd_sycophancy-5t_diff_sycophant", "output_dir": "/projects/nlp/data/constanzam/weight-interp/task-vectors/math_non_sycophant_12Aug", "scaling_coef": 1.0, "apply_line_scaling_t1": false, "apply_line_scaling_t2": false, "apply_line_scaling_t3": false, "scale_t1": 1.0, "scale_t2": 5.0, "scale_t3": 5.0 }
ggozzy/blockassist-bc-stubby_yapping_mandrill_1755791867
ggozzy
2025-08-21T15:59:07Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "stubby yapping mandrill", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:58:52Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - stubby yapping mandrill --- # 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_1755791865
Dejiat
2025-08-21T15:58:19Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:58:13Z
--- 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).
Dongkkka/ffw_sg2_rev1_PickCoffeePetEdit_SmolVLA
Dongkkka
2025-08-21T15:56:39Z
0
0
lerobot
[ "lerobot", "safetensors", "robotics", "smolvla", "dataset:Dongkkka/ffw_sg2_rev1_PickCoffeePetEdit", "arxiv:2506.01844", "base_model:lerobot/smolvla_base", "base_model:finetune:lerobot/smolvla_base", "license:apache-2.0", "region:us" ]
robotics
2025-08-21T15:55:52Z
--- base_model: lerobot/smolvla_base datasets: Dongkkka/ffw_sg2_rev1_PickCoffeePetEdit library_name: lerobot license: apache-2.0 model_name: smolvla pipeline_tag: robotics tags: - robotics - lerobot - smolvla --- # 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
ashifootp/blockassist-bc-shaggy_stocky_seal_1755791643
ashifootp
2025-08-21T15:55:29Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "shaggy stocky seal", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:55:24Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - shaggy stocky seal --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
thanobidex/blockassist-bc-colorful_shiny_hare_1755790000
thanobidex
2025-08-21T15:53:58Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "colorful shiny hare", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:53:54Z
--- 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).
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755789733
katanyasekolah
2025-08-21T15:52:52Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "silky sprightly cassowary", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:52:49Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - silky sprightly cassowary --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
manusiaperahu2012/blockassist-bc-roaring_long_tuna_1755789949
manusiaperahu2012
2025-08-21T15:52:36Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "roaring long tuna", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:52:33Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - roaring long tuna --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Hq-Link-Abigail-video-viral-original/LINK.VIDEOS.Abigail.Viral.Video.Official.Clip
Hq-Link-Abigail-video-viral-original
2025-08-21T15:51:12Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:50:55Z
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
Vasya777/blockassist-bc-lumbering_enormous_sloth_1755791394
Vasya777
2025-08-21T15:50:33Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "lumbering enormous sloth", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:50:25Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - lumbering enormous sloth --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
ggozzy/blockassist-bc-stubby_yapping_mandrill_1755791330
ggozzy
2025-08-21T15:50:07Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "stubby yapping mandrill", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:49:54Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - stubby yapping mandrill --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
2hpsatt/blockassist-bc-huge_deft_eagle_1755791291
2hpsatt
2025-08-21T15:49:32Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "huge deft eagle", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:49:24Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - huge deft eagle --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Original-Uppal-Farm-Girl-Viral-Video-Clip/New.full.videos.Uppal.Farm.Girl.Viral.Video.Official.Tutorial
Original-Uppal-Farm-Girl-Viral-Video-Clip
2025-08-21T15:48:59Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:48:44Z
<animated-image data-catalyst=""><a href="https://tinyurl.com/3ckkv2u7?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>
rvipitkirubbe/blockassist-bc-mottled_foraging_ape_1755789603
rvipitkirubbe
2025-08-21T15:47:02Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "mottled foraging ape", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:46:59Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - mottled foraging ape --- # 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_1755791186
Dejiat
2025-08-21T15:46:59Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:46:54Z
--- 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).
nvidia/Nemotron-H-47B-Reasoning-128K-FP8
nvidia
2025-08-21T15:46:36Z
57
5
transformers
[ "transformers", "safetensors", "nvidia", "pytorch", "text-generation", "conversational", "en", "arxiv:2504.03624", "arxiv:2505.00949", "license:other", "endpoints_compatible", "region:us" ]
text-generation
2025-05-29T21:46:29Z
--- library_name: transformers license: other license_name: nvidia-internal-scientific-research-and-development-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/ pipeline_tag: text-generation language: - en tags: - nvidia - pytorch --- # Nemotron-H-47B-Reasoning-128K-FP8 **Model Developer:** NVIDIA **Model Dates:** October 2024 \- March 2025 **Data Freshness:** September 2024 The pretraining data has a cutoff date of September 2024\. ## Model Overview NVIDIA Nemotron-H-47B-Reasoning-128K-FP8 is a large language model (LLM) developed by NVIDIA, designed as a unified model for both reasoning and non-reasoning tasks.It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model uses a hybrid architecture consisting primarily of Mamba-2 and MLP layers combined with just five Attention layers. It is based on [Nemotron-H-47B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-47B-Base-8K), which is a pruned and distilled from [Nemotron-H-56B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-56B-Base-8K). The supported languages include: English, German, Spanish, French, Italian, Korean, Portuguese, Russian, Japanese, and Chinese. We provide a BF16 checkpoint which can be used with HuggingFace-Transformers or TensorRT-LLM, and a FB8 checkpoint which can be used with TensorRT-LLM. This model is for research and development only. ## License/Terms of Use GOVERNING TERMS: Use of this model is governed by the [NVIDIA Internal Scientific Research and Development Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/) ## Model Architecture - Architecture Type: Mamba2-Transformer Hybrid - Network Architecture: Nemotron-Hybrid This model has 47B of model parameters following [Nemotron-H-47B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-47B-Base-8K). ### Deployment Geography: Global ### Use Case: This model is intended for developers and researchers building LLMs ### Release Date: 06/06/2025 Huggingface 06/06/2025 via [https://huggingface.co/](https://huggingface.co/) ## References - [\[2504.03624\] Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models](https://arxiv.org/abs/2504.03624) - [\[2505.00949\] Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949) ## Input - Input Type(s): Text - Input Format(s): String - Input Parameters: One-Dimensional (1D): Sequences - Other Properties Related to Input: Context length up to 128K. Supported languages include German, Spanish, French, Italian, Korean, Portuguese, Russian, Japanese, Chinese and English. ## Output - Output Type(s): Text - Output Format: String - Output Parameters: One-Dimensional (1D): Sequences Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration - Runtime Engine(s): NeMo 24.09 - Supported Hardware Microarchitecture Compatibility: NVIDIA H100-80GB, NVIDIA A100 - Operating System(s): Linux ### **Use it with Transformers** The snippet below shows how to use this model with Huggingface Transformers (tested on version 4.48.3). ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM # Load tokenizer and model tokenizer = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-47B-Reasoning-128K") model = AutoModelForCausalLM.from_pretrained( "nvidia/Nemotron-H-47B-Reasoning-128K", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto" ) ``` Case 1: No reasoning signal provided in system prompt, model behaves in “Auto” mode. ``` messages = [ {"role": "system", "content": ""}, {"role": "user", "content": "Write a haiku about GPUs"}, ] ``` Case 2: Reasoning set to True ``` messages = [ {"role": "system", "content": "{'reasoning': True}"}, {"role": "user", "content": "Write a haiku about GPUs"}, ] ``` Case 3: Reasoning set to False ``` messages = [ {"role": "system", "content": "{'reasoning': False}"}, {"role": "user", "content": "Write a haiku about GPUs"}, ] ``` The rest of the inference snippet remains the same ``` tokenized_chat = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt" ).to(model.device) outputs = model.generate( tokenized_chat, max_new_tokens=32, eos_token_id=tokenizer.eos_token_id ) print(tokenizer.decode(outputs[0])) ``` We recommend setting `temperature` to `0.6`, `top_p` to `0.95` , and increase `max_new_tokens` to `1024` or higher for reasoning True. ### **Use it with TensorRT-LLM** The snippet below shows how to use this model with TensorRT-LLM. We tested this on the following [commit](https://github.com/NVIDIA/TensorRT-LLM/tree/46c5a564446673cdd0f56bcda938d53025b6d04e) and followed these [instructions](https://github.com/NVIDIA/TensorRT-LLM/blob/46c5a564446673cdd0f56bcda938d53025b6d04e/docs/source/installation/build-from-source-linux.md#option-2-build-tensorrt-llm-step-by-step) to build and install TensorRT-LLM in a docker container. ``` from tensorrt_llm import SamplingParams from tensorrt_llm._torch import LLM from tensorrt_llm._torch.pyexecutor.config import PyTorchConfig from tensorrt_llm.llmapi import KvCacheConfig from transformers import AutoTokenizer pytorch_config = PyTorchConfig( disable_overlap_scheduler=True, enable_trtllm_decoder=True ) kv_cache_config = KvCacheConfig( enable_block_reuse=False, ) ``` For **BF16** Checkpoint use: ``` model_id = "nvidia/Nemotron-H-47B-Reasoning-128K" ``` For **FP8** Checkpoint use: ``` model_id = "nvidia/Nemotron-H-47B-Reasoning-128K-FP8" ``` The rest of the inference remains the same for BF16 and FP8 ``` tokenizer = AutoTokenizer.from_pretrained(model_id) llm = LLM( model=model_id, max_seq_len=32678, max_batch_size=4, pytorch_backend_config=pytorch_config, kv_cache_config=kv_cache_config, tensor_parallel_size=8, ) messages = [ {"role": "system", "content": "{'reasoning': True}"}, {"role": "user", "content": "Write a haiku about GPUs"}, ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) sampling_params = SamplingParams( max_tokens=512, temperature=0.6, top_p=0.95, add_special_tokens=False, ) outputs = llm.generate([prompt], sampling_params) print(outputs[0].outputs[0].text) ``` ## Model Version - v1.0 ## Prompt Format We follow the jinja chat template provided below. This template conditionally adds `<think>\n` to the start of the Assistant response if `{'reasoning': True}` is found in the system prompt and adds `<think></think>` to the start of the Assistant response if `{'reasoning': False}` is found the system prompt. Thus enforcing reasoning on/off behavior. If neither `{'reasoning': True}` or `{'reasoning': False}` is found in the system prompt the model can choose either manner to respond. Note that the system prompt can contain other instructions apart from just `{'reasoning': True}` or `{'reasoning': False}` ``` {{ '<SPECIAL_10>System\n' }}{%- if messages and messages[0]['role'] == 'system' -%}{%- set sys_content = messages[0]['content'].strip() -%}{%- set sys_content = sys_content.replace(\"{'reasoning': True}\", '').replace(\"{'reasoning': False}\", '').lstrip('\n') -%}{{ sys_content + '\n' if sys_content else '' }}{%- endif -%}{% for message in (messages[1:] if messages[0]['role'] == 'system' else messages) %}{%- if message['role'] == 'user' -%}{{ '\n<SPECIAL_11>User\n' + message['content'].strip() }}{%- if loop.last -%}{{ '\n<SPECIAL_11>Assistant\n' }}{%- if messages[0]['role'] == 'system' -%}{%- if \"{'reasoning': True}\" in messages[0]['content'] -%}{{ '<think>\n' }}{%- elif \"{'reasoning': False}\" in messages[0]['content'] -%}{{ '<think></think>' }}{%- endif -%}{%- endif -%}{%- endif -%}{%- elif message['role'] == 'assistant' -%}{{ message['content'].strip() }}{%- endif -%}{%- endfor -%} ``` ## Training, Testing, and Evaluation Datasets The post-training corpus for Nemotron-H-47B-Reasoning-128K consists of English and multilingual text (German, Spanish, French, Italian, Korean, Portuguese, Russian, Japanese, Chinese and English). Our sources cover a variety of document types such as: webpages, dialogue, articles, and other written materials. The corpus spans domains including code, legal, math, science, finance, and more. We also include a small portion of question-answering, and alignment style data to improve model accuracies. For several of the domains listed above we used syntheitc data, specifically reasoning traces, from DeepSeek R1. **Data Collection for Training & Testing Datasets:** Hybrid: Automated, Human, Synthetic **Data Labeling for Training & Testing Datasets:** Hybrid: Automated, Human, Synthetic ### Evaluation ### Benchmark Results (Reasoning On) We evaluated our BF16 and FP8 models in **Reasoning-On** mode against [Llama-Nemotron Super V1](https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1), using the same prompt formats across all benchmarks. The FP8 version shows negligible performance difference compared to the BF16 model. | Benchmark | Llama-Nemotron Super(49B) V1 | Nemotron-H 47B Reasoning | Nemotron-H 47B Reasoning (FP8) | |--------------------|--------------------------------------------------------|---------------------------|-------------------------------| | AIME25 | 53.00% | 54.17% | 54.17% | | MATH500 | 96.60% | 96.20% | 96.80% | | GPQA | 65.10% | 65.66% | 64.65% | | MBPP | 90.20% | 91.80% | 91.80% | | MBPP_PLUS | 75.10% | 79.90% | 79.90% | | LCB | 41.22% | 50.18% | 53.41% | | BFCL | 72.68% | 72.95% | 73.21% | | IFEVAL-Prompt | 81.80% | 84.47% | 84.47% | | IFEVAL-Instruction | 87.40% | 89.69% | 89.57% | | Arena Hard | 85.00% | 85.00% | - | ## Potential Known Risks for Usage The model was trained on data that contains toxic language, unsafe content, and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. The model demonstrates weakness to indirect prompt injection via some encodings, including Base16, Hex/ASCII, and Braille, though it is more resilient than other similar models to injections using the more common Base64 vector. ## Inference - Engines: HF, vLLM, TensorRT-LLM - Test Hardware NVIDIA H100-80GB ## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755790033
Sayemahsjn
2025-08-21T15:46:10Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "playful feline octopus", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:46:06Z
--- 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).
PAPOGalaxy/PAPO-G-NRef-Qwen2.5-VL-7B
PAPOGalaxy
2025-08-21T15:45:58Z
0
0
transformers
[ "transformers", "safetensors", "image-text-to-text", "dataset:PAPOGalaxy/PAPO_train", "arxiv:2507.06448", "license:mit", "endpoints_compatible", "region:us" ]
image-text-to-text
2025-07-08T17:08:42Z
--- datasets: - PAPOGalaxy/PAPO_train license: mit pipeline_tag: image-text-to-text library_name: transformers --- # PAPO Model This is the official model for the paper [**Perception-Aware Policy Optimization for Multimodal Reasoning**](https://huggingface.co/papers/2507.06448). ## Abstract Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored to purely textual domains, resulting in suboptimal performance when applied to multimodal reasoning tasks. In particular, we observe that a major source of error in current multimodal reasoning lies in the perception of visual inputs. To address this bottleneck, we propose **Perception-Aware Policy Optimization (PAPO)**, a simple yet effective extension of GRPO that encourages the model to learn to perceive while learning to reason, entirely from internal supervision signals. Notably, PAPO does not rely on additional data curation, external reward models, or proprietary models. Specifically, we introduce the Implicit Perception Loss in the form of a KL divergence term to the GRPO objective, which, despite its simplicity, yields significant overall improvements (4.4%) on diverse multimodal benchmarks. The improvements are more pronounced, approaching 8.0%, on tasks with high vision dependency. We also observe a substantial reduction (30.5%) in perception errors, indicating improved perceptual capabilities with PAPO. We conduct comprehensive analysis of PAPO and identify a unique loss hacking issue, which we rigorously analyze and mitigate through a Double Entropy Loss. Overall, our work introduces a deeper integration of perception-aware supervision into RLVR learning objectives and lays the groundwork for a new RL framework that encourages visually grounded reasoning. **Project Page**: [https://mikewangwzhl.github.io/PAPO/](https://mikewangwzhl.github.io/PAPO/) **Code**: [https://github.com/mikewangwzhl/PAPO](https://github.com/mikewangwzhl/PAPO) ## Model Version PAPO (NO KL_ref) ## Usage This model is designed for multimodal reasoning tasks, taking both image and text inputs to generate text. You can load it using the `transformers` library. For detailed usage instructions, including how to prepare multimodal inputs, please refer to the official project page and code repository. ```python from transformers import AutoProcessor, AutoModelForCausalLM import torch model_id = "mikewangwzhl/PAPO-7B-NO-KL" # Or the specific model identifier on the Hub # Load processor and model processor = AutoProcessor.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16) # Move model to appropriate device (e.g., GPU if available) if torch.cuda.is_available(): model = model.to("cuda") # Example of a text-only generation (if supported by the multimodal model) # For full multimodal usage, you would also prepare and pass image data. prompt = "Hello, what can you do?" messages = [{"role": "user", "content": prompt}] # Apply chat template and get input IDs input_ids = processor.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt") if torch.cuda.is_available(): input_ids = input_ids.to("cuda") # Generate a response output_ids = model.generate(input_ids, max_new_tokens=100) # Decode the generated text generated_text = processor.decode(output_ids[0], skip_special_tokens=True) print(generated_text) ```
PAPOGalaxy/PAPO-G-Qwen2.5-VL-3B
PAPOGalaxy
2025-08-21T15:45:32Z
0
0
transformers
[ "transformers", "safetensors", "image-text-to-text", "dataset:PAPOGalaxy/PAPO_train", "arxiv:2507.06448", "license:mit", "endpoints_compatible", "region:us" ]
image-text-to-text
2025-07-08T05:41:52Z
--- datasets: - PAPOGalaxy/PAPO_train license: mit pipeline_tag: image-text-to-text library_name: transformers --- # PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning This is the official model released for our paper [Perception-Aware Policy Optimization for Multimodal Reasoning](https://huggingface.co/papers/2507.06448). **Project Page:** [https://mikewangwzhl.github.io/PAPO/](https://mikewangwzhl.github.io/PAPO/) **Code:** [https://github.com/mikewangwzhl/PAPO](https://github.com/mikewangwzhl/PAPO) ## Model Version PAPO (γ=0.01) ## Usage You can use this model with the Hugging Face `transformers` library. ```python from transformers import AutoProcessor, AutoModelForCausalLM from PIL import Image import requests # Replace "PAPOGalaxy/PAPO" with the actual model ID if different # For example, if it's PAPOGalaxy/PAPO-7B or PAPOGalaxy/PAPO-3B model_id = "PAPOGalaxy/PAPO" processor = AutoProcessor.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") # Example image (replace with your own image path or URL) image_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/bee.JPG" image = Image.open(requests.get(image_url, stream=True).raw) # Example prompt prompt = "What is in the image?" # Prepare inputs following the model's chat template messages = [ {"role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": prompt} ]} ] text = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) inputs = processor(text=text, images=image, return_tensors="pt").to(model.device) # Generate response generated_ids = model.generate(**inputs, max_new_tokens=100) generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] print(generated_text) ```
nvidia/Nemotron-H-47B-Base-8K
nvidia
2025-08-21T15:45:32Z
178
21
transformers
[ "transformers", "safetensors", "nvidia", "pytorch", "nemotron-h", "text-generation", "en", "de", "es", "fr", "it", "ko", "pt", "ru", "jp", "zh", "arxiv:2504.03624", "base_model:nvidia/Nemotron-H-56B-Base-8K", "base_model:finetune:nvidia/Nemotron-H-56B-Base-8K", "license:other", "endpoints_compatible", "region:us" ]
text-generation
2025-04-08T17:36:17Z
--- library_name: transformers license: other license_name: nvidia-internal-scientific-research-and-development-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/ pipeline_tag: text-generation language: - en - de - es - fr - it - ko - pt - ru - jp - zh tags: - nvidia - pytorch - nemotron-h base_model: - nvidia/Nemotron-H-56B-Base-8K --- # Nemotron-H-47B-Base-8K ## Model Overview NVIDIA Nemotron-H-47B-Base-8K is a large language model (LLM) developed by NVIDIA, designed as a completion model for a given piece of text. It uses a hybrid model architecture that consists primarily of Mamba-2 and MLP layers combined with just five Attention layers. The model is pruned and distilled from [Nemotron-H-56B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-56B-Base-8K) using 63B tokens, and features an 8K context length. The supported languages include: English, German, Spanish, French, Italian, Korean, Portuguese, Russian, Japanese, and Chinese. For more detailed information on the model architecture, training, and evaluation, please see the [project page](https://research.nvidia.com/labs/adlr/nemotronh/) and the [technical report](https://arxiv.org/abs/2504.03624). For best performance on a given task, users are encouraged to customize the model using the [NeMo Framework](https://docs.nvidia.com/nemo-framework/index.html) suite of customization tools including Parameter-Efficient Fine-Tuning (P-tuning, Adapters, LoRA, and more), and Model Alignment (SFT, SteerLM, RLHF, and more) using [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner). This model is for research and development only. This model is part of the Nemotron-H Collection. You can find the models in this family here: - [Nemotron-H-56B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-56B-Base-8K) - [Nemotron-H-47B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-47B-Base-8K) - [Nemotron-H-8B-Base-8K](https://huggingface.co/nvidia/Nemotron-H-8B-Base-8K) ## License/Terms of Use GOVERNING TERMS: Use of this model is governed by the [NVIDIA Internal Scientific Research and Development Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/). **Model Developer:** NVIDIA **Model Dates:** October 2024 - March 2025 **Data Freshness:** September 2024 The pretraining data has a cutoff date of September 2024. ## Use Case: This model is intended for developers and researchers building LLMs. ## Release Date: 4/12/2025 ## References - [\[2504.03624\] Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models](https://arxiv.org/abs/2504.03624) ## Model Architecture - Architecture Type: Hybrid Mamba-Transformer - Network Architecture: Nemotron-H This model has 47B model parameters. ## Input - Input Type(s): Text - Input Format(s): String - Input Parameters: One-Dimensional (1D): Sequences - Other Properties Related to Input: Context length up to 8K. Supported languages include German, Spanish, French, Italian, Korean, Portuguese, Russian, Japanese, Chinese and English. ## Output - Output Type(s): Text - Output Format: String - Output Parameters: One-Dimensional (1D): Sequences Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration - Runtime Engine(s): NeMo 24.12 - Supported Hardware Microarchitecture Compatibility: NVIDIA H100-80GB, NVIDIA A100 - Operating System(s): Linux ## Model Version - v1.0 ## Prompt Format As this is a base model, no explicit prompt format is recommended or required. ### Example ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM # Load the tokenizer and model tokenizer = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-47B-Base-8K", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-47B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto") prompt = "When was NVIDIA founded?" outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device)) print(tokenizer.decode(outputs[0])) ``` ## Training, Testing, and Evaluation Datasets ### Training & Testing Datasets: The training corpus for Nemotron-H-47B-Base-8K consists of English and multilingual text (German, Spanish, French, Italian, Korean, Portuguese, Russian, Japanese, Chinese and English), as well as code. Our sources cover a variety of document types such as: webpages, dialogue, articles, and other written materials. This model was also improved using synthetic data from Qwen (Built with Qwen). The corpus spans domains including legal, math, science, finance, and more. We also include a small portion of question-answering, and alignment style data to improve model accuracies. **Data Collection for Training & Testing Datasets:** Hybrid: Automated, Human, Synthetic **Data Labeling for Training & Testing Datasets:** Hybrid: Automated, Human, Synthetic ### Evaluation Datasets We used the datasets listed in the next section to evaluate the model. **Data Collection for Training Datasets:** Hybrid: Automated, Human, Synthetic **Data Labeling for Training Datasets:** Hybrid: Automated, Human, Synthetic #### Commonsense Understanding Evaluations: | ARC Challenge 25-shot | Hellaswag 10-shot | Winogrande 5-shot | CommonsenseQA 7-shot | |-------------|--------------|-----------------|------------------| | 94.6 | 87.9 | 83.9 | 87.3 | - ARC (Ai2 reasoning challenge)-Challenge - The challenge set of questions from a benchmark that contains grade-school level, multiple-choice science questions to assess question answering ability of language models. [Dataset](https://huggingface.co/datasets/allenai/ai2_arc) - Hellaswag - Tests the ability of a language model to correctly finish the provided context from a choice of possible options. [Dataset](https://huggingface.co/datasets/Rowan/hellaswag ) - Winogrande - Tests the ability to choose the right option for a given sentence which requires commonsense reasoning. [Dataset](https://huggingface.co/datasets/allenai/winogrande ) - CommonsenseQA - A multiple-choice question answering dataset that requires different type of commonsense knowledge to predict the correct answers. [Dataset](https://huggingface.co/datasets/tau/commonsense_qa ) #### Coding Evaluations: | MBPP(sanitized) 3-shot | MBPP+ 0-shot | HumanEval 0-shot | HumanEval+ 0-shot | |-------------|--------------|-----------------|------------------| | 75.9 | 65.6| 61.0 | 56.1 | - MBPP (Mostly Basic Python Programming Problems) - Evaluates ability to generate solutions for Python programming tasks. [Dataset](https://github.com/google-research/google-research/tree/master/mbpp) - MBPP+ - Extended version of MBPP with additional validation. [Dataset](https://huggingface.co/datasets/evalplus/mbppplus) - HumanEval - Tests code generation and completion abilities in Python. [Dataset](https://github.com/openai/human-eval) #### Math Evaluations: | GSM8K 8-shot CoT | MATH 4-shot CoT | MATH-Lvl 5 4-shot CoT | MATH-500 4-shot CoT | |--------------|------------|------------|------------| | 93.3 | 57.4 | 34.2 | 57.9 | - GSM8K (Grade School Math 8K) - Evaluates grade school level mathematical word problem solving. [Dataset](https://github.com/openai/grade-school-math) - MATH-500 - Tests advanced mathematical problem solving across algebra, geometry, and calculus. [Dataset](https://huggingface.co/datasets/HuggingFaceH4/MATH-500) - MATH Lvl 5 - Only the most difficult questions from the MATH dataset. [Dataset](https://github.com/hendrycks/math) - MATH-500 - Tests advanced mathematical problem solving across algebra, geometry, and calculus. [Dataset](https://huggingface.co/datasets/HuggingFaceH4/MATH-500) #### General Evaluations: | MMLU-Pro 5-shot-cot | MMLU 5-shot | |------------------|------------| | 61.8 | 83.6 | - MMLU - Tests knowledge across 57 subjects including science, humanities, math and more. [Dataset](https://github.com/hendrycks/test) - MMLU Pro - Evaluates language understanding models across a broad range of challenging, reasoning-focused questions across 14 diverse domains. [Dataset](https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro) ## Potential Known Risks for Usage The model was trained on data that contains toxic language, unsafe content, and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. The model demonstrates weakness to indirect prompt injection via some encodings, including Base16, Hex/ASCII, and Braille, though is more resilient than other similar models to injections using the more common Base64 vector. ## Inference - Engine: NeMo - Test Hardware NVIDIA H100-80GB ## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Responsible Use Guide available at http://nvidia.com/nemotron-responsible-use. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
VIDEO-DE-MILICA-Y-ANGEL-DAVID-ORIGINAL/VER-Milica.y.Angel.David.Video.Debut.Erome.Video.de.Milica.y.Angel.David.ybanez.Jugar
VIDEO-DE-MILICA-Y-ANGEL-DAVID-ORIGINAL
2025-08-21T15:43:27Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:43:15Z
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
viraja1/banking
viraja1
2025-08-21T15:43:23Z
5
0
transformers
[ "transformers", "safetensors", "gemma3_text", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:unsloth/gemma-3-270m-it", "base_model:finetune:unsloth/gemma-3-270m-it", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-generation
2025-08-19T17:40:17Z
--- base_model: unsloth/gemma-3-270m-it tags: - text-generation-inference - transformers - unsloth - gemma3_text license: apache-2.0 language: - en --- # Uploaded finetuned model - **Developed by:** viraja1 - **License:** apache-2.0 - **Finetuned from model :** unsloth/gemma-3-270m-it This gemma3_text 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)
PAPOGalaxy/PAPO-G-Qwen2.5-VL-7B
PAPOGalaxy
2025-08-21T15:43:19Z
0
1
transformers
[ "transformers", "safetensors", "multimodal", "qwen2_5", "image-text-to-text", "dataset:PAPOGalaxy/PAPO_train", "arxiv:2507.06448", "license:mit", "endpoints_compatible", "region:us" ]
image-text-to-text
2025-07-08T17:07:36Z
--- datasets: - PAPOGalaxy/PAPO_train license: mit pipeline_tag: image-text-to-text library_name: transformers tags: - multimodal - qwen2_5 --- # PAPO Model This repository contains the official model checkpoint for the paper **[Perception-Aware Policy Optimization for Multimodal Reasoning](https://arxiv.org/abs/2507.06448)**. ## About Perception-Aware Policy Optimization (PAPO) is a novel approach that extends Reinforcement Learning with Verifiable Rewards (RLVR) to significantly enhance multimodal reasoning abilities in Large Language Models (LLMs). Addressing a major bottleneck where up to 67% of errors stem from poor visual perception rather than logical reasoning, PAPO encourages the model to learn to perceive while simultaneously learning to reason. This is achieved entirely through internal supervision signals, eliminating the need for additional data curation, external reward models, or proprietary models. Specifically, PAPO integrates an Implicit Perception Loss as a KL divergence term within the GRPO objective. Despite its simplicity, this yields significant overall improvements (4.4%) on diverse multimodal benchmarks, with even more pronounced gains (approaching 8.0%) on vision-dependent tasks. It also notably reduces perception errors by 30.5%, demonstrating improved perceptual capabilities. PAPO serves as a direct drop-in replacement for GRPO. ## Project Page Find more details, visualizations, and updates on the official project page: [https://mikewangwzhl.github.io/PAPO/](https://mikewangwzhl.github.io/PAPO/) ## Code The official code repository for PAPO is available here: [https://github.com/mikewangwzhl/PAPO](https://github.com/mikewangwzhl/PAPO) ## Model Version PAPO (γ=0.01) ## Usage This model can be easily loaded and used with the `transformers` library. ```python from transformers import AutoProcessor, AutoModelForCausalLM from PIL import Image import requests from io import BytesIO # Replace "PAPOGalaxy/PAPO-Qwen2_5-7B-VL" with the actual model ID if different # The official checkpoints are available at: https://huggingface.co/collections/PAPOGalaxy/papo-qwen-686d92dd3d43b1ce698f851a model_id = "PAPOGalaxy/PAPO-Qwen2_5-7B-VL" processor = AutoProcessor.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) # Example: Describe an image from a URL image_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/bee.JPG" try: image = Image.open(BytesIO(requests.get(image_url).content)) except Exception as e: print(f"Error loading image from URL: {e}. Please ensure the URL is valid or use a local path.") exit() prompt = "Describe this image in detail." # Prepare inputs for the model inputs = processor(images=image, text=prompt, return_tensors="pt") # Generate a response print("Generating response...") generated_ids = model.generate(**inputs, max_new_tokens=512) # Decode the generated text generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] print("Generated text:") print(generated_text) # Example: Answer a question about an image prompt_qa = "What is the main subject of this image?" inputs_qa = processor(images=image, text=prompt_qa, return_tensors="pt") generated_ids_qa = model.generate(**inputs_qa, max_new_tokens=100) generated_text_qa = processor.batch_decode(generated_ids_qa, skip_special_tokens=True)[0] print(" Generated QA response:") print(generated_text_qa) ```
Brown-kudi-instagram/New.full.videos.brown.kudi.instagram.Viral.Video.Official.Tutorial
Brown-kudi-instagram
2025-08-21T15:42:08Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:41:56Z
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
Orginal-Kamangyan-viral-video-Clip/New.full.videos.Kamangyan.Viral.Video.Official.Tutorial
Orginal-Kamangyan-viral-video-Clip
2025-08-21T15:39:57Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:39:45Z
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
BootesVoid/cmelhk5j003cjtlqbft4amwuw_cmeliqwvu03h4tlqbb8s37z15
BootesVoid
2025-08-21T15:39:46Z
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
2025-08-21T15:39:44Z
--- 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: ROYA --- # Cmelhk5J003Cjtlqbft4Amwuw_Cmeliqwvu03H4Tlqbb8S37Z15 <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 `ROYA` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "ROYA", "lora_weights": "https://huggingface.co/BootesVoid/cmelhk5j003cjtlqbft4amwuw_cmeliqwvu03h4tlqbb8s37z15/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/cmelhk5j003cjtlqbft4amwuw_cmeliqwvu03h4tlqbb8s37z15', weight_name='lora.safetensors') image = pipeline('ROYA').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: 2500 - Learning rate: 9e-05 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cmelhk5j003cjtlqbft4amwuw_cmeliqwvu03h4tlqbb8s37z15/discussions) to add images that show off what you’ve made with this LoRA.
2hpsatt/blockassist-bc-huge_deft_eagle_1755790692
2hpsatt
2025-08-21T15:39:41Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "huge deft eagle", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:39:37Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - huge deft eagle --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
X-N-X-Original-Uppal-Farm-Girl-Viral-Video/Uppal.Farm.Girl.Viral.Video.Original.Link.Official
X-N-X-Original-Uppal-Farm-Girl-Viral-Video
2025-08-21T15:39:01Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:38:53Z
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a> <a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
Vasya777/blockassist-bc-lumbering_enormous_sloth_1755790686
Vasya777
2025-08-21T15:38:47Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "lumbering enormous sloth", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:38:38Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - lumbering enormous sloth --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
ashifootp/blockassist-bc-shaggy_stocky_seal_1755790538
ashifootp
2025-08-21T15:37:17Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "shaggy stocky seal", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:36:56Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - shaggy stocky seal --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
pburke1234/Qwen3-0.6B-Gensyn-Swarm-exotic_masked_chicken
pburke1234
2025-08-21T15:36:56Z
0
0
transformers
[ "transformers", "safetensors", "qwen3", "text-generation", "rl-swarm", "genrl-swarm", "grpo", "gensyn", "I am exotic_masked_chicken", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T11:29:28Z
--- library_name: transformers tags: - rl-swarm - genrl-swarm - grpo - gensyn - I am exotic_masked_chicken --- # 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]
Dejiat/blockassist-bc-savage_unseen_bobcat_1755790565
Dejiat
2025-08-21T15:36:40Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:36:34Z
--- 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).
calegpedia/blockassist-bc-stealthy_slimy_rooster_1755788984
calegpedia
2025-08-21T15:36:02Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "stealthy slimy rooster", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:35:59Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - stealthy slimy rooster --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Hans-Christian/gemma-finetune-gguf
Hans-Christian
2025-08-21T15:35:19Z
0
0
transformers
[ "transformers", "safetensors", "text-generation-inference", "unsloth", "gemma3_text", "trl", "en", "base_model:unsloth/gemma-3-270m-it", "base_model:finetune:unsloth/gemma-3-270m-it", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2025-08-21T15:34:56Z
--- base_model: unsloth/gemma-3-270m-it tags: - text-generation-inference - transformers - unsloth - gemma3_text - trl license: apache-2.0 language: - en --- # Uploaded model - **Developed by:** Hans-Christian - **License:** apache-2.0 - **Finetuned from model :** unsloth/gemma-3-270m-it This gemma3_text 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)
AIGym/AIGT-200k
AIGym
2025-08-21T15:34:36Z
0
0
transformers
[ "transformers", "en", "uk", "ru", "es", "de", "dataset:allenai/c4", "dataset:semran1/finemath_2048", "dataset:motionlabs/fineweb-ultra-mini", "dataset:macrocosm-os/code-parrot-github-code", "license:mit", "endpoints_compatible", "region:us" ]
null
2025-08-21T15:22:35Z
--- library_name: transformers license: mit datasets: - allenai/c4 - semran1/finemath_2048 - motionlabs/fineweb-ultra-mini - macrocosm-os/code-parrot-github-code language: - en - uk - ru - es - de --- ## **Model Card: AIGT-200k** ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63f2b7bcbe95ed4c9a9e7669/2GfDIlDKz4Ue9ItqWj7lT.png) ### **Model Details** * **Model Type:** Byte-Pair Encoding (BPE) Tokenizer * **Vocabulary Size:** ~200,000 * **Developed by:** AIGym Community * **Language(s):** Multilingual, with a focus on English, German, Ukrainian, Spanish, Russian, and Code. ### **Model Description** **AIGT-200k** is a highly efficient, multilingual Byte-Pair Encoding (BPE) tokenizer with a vocabulary of approximately 200,000. It is designed for modern large language models that require a nuanced understanding of conversational structure, multilingual text, and programming languages. This tokenizer was developed using a hybrid approach. It starts with a large base of predefined tokens, including the top 100,000 most common words, common symbols, and byte-level fallbacks. This foundation is then expanded through BPE training on a diverse corpus of text and code. A key feature of this tokenizer is its native support for the **OpenAI Harmony chat template**. This includes a rich set of special tokens for managing conversational flow, tool usage, and role specification, making it ideal for building advanced, agentic AI systems. It also maintains backward compatibility with the popular ChatML format. The tokenizer includes dedicated special tokens for multimodal applications and code infilling tasks, reserving tokens for future capabilities like image, video, and audio processing. ### **Motivation and Philosophy** The primary motivation behind **AIGT-200k** is to move towards a **universal, multi-capable tokenizer** that can serve as a standard for a wide range of AI applications. Instead of creating a tokenizer for a specific dataset or a single task, our goal is to establish a common foundation that supports: * **Multilingualism:** Seamlessly handling multiple human languages. * **Multimodality:** Providing the necessary tokens to integrate text with other data types like images and audio. * **Multi-Chat Templates:** Natively supporting both modern (OpenAI Harmony) and established (ChatML) conversational formats. By creating a versatile and comprehensive tokenizer, we hope to encourage the community to conform towards a shared standard. This will make models more interoperable, simplify fine-tuning, and allow collective efforts to focus on improving a single, powerful tokenization scheme. Crucially, **this tokenizer was designed specifically to tokenize questions, instructions, and agentic interactions**, not just to process large, static datasets. Its vocabulary and special tokens are optimized for the dynamic, turn-by-turn nature of conversational AI. ### **Intended Uses & Limitations** #### **Intended Uses** This tokenizer is optimized for the following applications: * **Advanced Chatbots and Conversational AI:** Native support for the Harmony and ChatML formats allows for the development of sophisticated, multi-turn dialogue systems. * **Multilingual Models:** Trained on a diverse set of languages to ensure broad linguistic competence. * **Code Generation and Understanding:** A significant portion of the training data consists of code, and it includes special tokens for infilling tasks. * **Tool-Using Agents:** The Harmony special tokens provide a robust framework for models that interact with external tools and APIs. * **Foundation Models:** Serves as a strong vocabulary base for training new large language models from scratch. #### **Limitations and Bias** * While trained on a multilingual dataset, the tokenizer's performance will be strongest on the languages most represented in the training data (English, German, Ukrainian, Spanish, Russian, and code). * The training data is sourced from large, unfiltered web crawls (like C4) and code repositories. As such, the tokenizer may have learned to represent societal biases, stereotypes, and potentially offensive language present in that data. Models trained using this tokenizer may generate content reflecting these biases. ### **How to Use** The tokenizer can be loaded and used directly from the Hugging Face Hub with the `AutoTokenizer` or `PreTrainedTokenizerFast` classes. ```python from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("AIGym/AIGT-200k") # Example of encoding an agentic prompt prompt = "<|start|><|message|><|user|>\nWhat is the weather in London?<|end|>" encoded = tokenizer(prompt) print(encoded["input_ids"]) # Example of decoding decoded = tokenizer.decode(encoded["input_ids"]) print(decoded) ``` ### **Training Data** The tokenizer was trained on a composite dataset designed for broad coverage. The training process involved two stages: 1. **Predefined Token Collection:** * `AIGym/top-100K-words`: A dataset of the 100,000 most frequent words. * `AIGym/common-for-tokens`: A collection of common numbers, symbols, emojis, and control characters. * A full set of 256 byte-level tokens to handle any unknown characters. 2. **BPE Training Corpus:** The BPE vocabulary was trained on a large, sampled dataset from the following sources: * **Code:** `macrocosm-os/code-parrot-github-code` (50,000 samples) * **Web Text (English):** `AIGym/motionlabs-fineweb-ultra-mini` (10,000 samples) * **Mathematical Text:** `AIGym/semran1-finemath_2048` (10,000 samples) * **Multilingual Web Text (C4):** * German (`de`): 2,500 samples * Ukrainian (`uk`): 5,000 samples * Spanish (`es`): 5,000 samples * Russian (`ru`): 5,000 samples * Multilingual Mix: 5,000 samples * English Multilingual Mix: 2,500 samples ### **Training Procedure** 1. **Normalization:** Text was normalized using NFKC and control characters were removed. 2. **Pre-tokenization:** A regex-based pre-tokenizer was used to split text based on linguistic patterns, numbers, and symbols. 3. **Model:** A Byte-Pair Encoding (BPE) model was used. 4. **Training:** The `BpeTrainer` from the `tokenizers` library was used to train the vocabulary on the corpus, building upon the predefined tokens to reach a final size of approximately 200,000. 5. **Special Tokens:** A comprehensive set of special tokens for control, multimodality, chat templates, and code infilling was added to the final vocabulary. The post-processor is configured to add `<|bos|>` and `<|eos|>` tokens to sequences. #### **Special Token Categories** * **Standard:** `<|unk|>`, `<|bos|>`, `<|eos|>`, `<|pad|>` * **ChatML & Harmony Roles:** `<|system|>`, `<|user|>`, `<|assistant|>`, `<|developer|>`, `<|tool|>` * **OpenAI Harmony Format:** `<|start|>`, `<|end|>`, `<|message|>`, `<|channel|>`, `<|call|>`, `<|return|>`, `<|constrain|>` * **Code Infilling:** `<|code_prefix|>`, `<|code_middle|>`, `<|code_suffix|>` * **Multimodality:** `<|img_start|>`, `<|img_end|>`, `<|IMAGE_SOFT_TOKEN|>` (and equivalents for audio/video) * **Reserved:** 105 reserved tokens for future expansion (`<|category_reserved_i|>`)
onceuponamiu/trocr_constance_de_salm_finetune
onceuponamiu
2025-08-21T15:34:33Z
0
0
transformers
[ "transformers", "safetensors", "vision-encoder-decoder", "image-to-text", "ocr", "handwritten-text-recognition", "trocr", "endpoints_compatible", "region:us" ]
image-to-text
2025-08-21T15:33:29Z
--- library_name: transformers tags: ["ocr", "handwritten-text-recognition", "vision-encoder-decoder", "trocr", "image-to-text"] --- # TrOCR - Handwritten Text Recognition Model A fine-tuned TrOCR (Transformer OCR) model for handwritten text recognition, built on the vision-encoder-decoder architecture. This model can transcribe handwritten text from images into machine-readable text. ## Model Details ### Model Description This is a TrOCR model that combines a Vision Transformer (ViT) encoder with a Transformer decoder to perform handwritten text recognition. The model has been trained to convert handwritten text images into text output. - **Developed by:** Fine-tuned from Microsoft's TrOCR architecture - **Model type:** Vision-Encoder-Decoder (TrOCR) - **Language(s):** Multi-language support (based on training data) - **License:** [Please specify your license] - **Finetuned from model:** Microsoft's TrOCR base model ### Model Architecture - **Encoder:** Vision Transformer (ViT) with 12 layers, 12 attention heads, 768 hidden size - **Decoder:** Transformer decoder with 12 layers, 16 attention heads, 1024 hidden size - **Image input:** 384x384 pixels, 3 channels (RGB) - **Vocabulary size:** 50,265 tokens - **Max sequence length:** 512 tokens ## Uses ### Direct Use This model is designed for: - **Handwritten text recognition** from images - **Document digitization** and transcription - **Historical document analysis** - **Form processing** and data extraction - **Educational applications** (grading handwritten assignments) ### Downstream Use The model can be fine-tuned for: - **Specific handwriting styles** or languages - **Domain-specific documents** (medical, legal, academic) - **Real-time OCR applications** - **Mobile OCR apps** ### Out-of-Scope Use - **Printed text recognition** (use standard OCR tools instead) - **Handwriting style analysis** or personality assessment - **Text generation** (this is a recognition model, not generative) - **Low-quality or extremely blurry images** ## Bias, Risks, and Limitations ### Limitations - **Image quality dependency:** Performance degrades with poor image quality - **Handwriting style variation:** May struggle with unusual or artistic handwriting - **Language bias:** Performance depends on training data language distribution - **Context sensitivity:** May misinterpret text without proper context ### Recommendations - Ensure input images are clear and well-lit - Use appropriate image preprocessing for optimal results - Validate outputs for critical applications - Consider domain-specific fine-tuning for specialized use cases ## How to Get Started with the Model ### Basic Usage ```python from transformers import TrOCRProcessor, VisionEncoderDecoderModel from PIL import Image # Load model and processor processor = TrOCRProcessor.from_pretrained("your-model-path") model = VisionEncoderDecoderModel.from_pretrained("your-model-path") # Load and process image image = Image.open("handwritten_text.jpg").convert("RGB") # Generate text pixel_values = processor(image, return_tensors="pt").pixel_values generated_ids = model.generate(pixel_values) generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] print(f"Recognized text: {generated_text}") ``` ### Requirements ```bash pip install transformers torch pillow ``` ## Training Details ### Training Data [Specify your training dataset details here] ### Training Procedure #### Preprocessing - Images resized to 384x384 pixels - Normalized with mean [0.5, 0.5, 0.5] and std [0.5, 0.5, 0.5] - RGB conversion and rescaling applied #### Training Hyperparameters - **Training regime:** [Specify training precision and regime] - **Image size:** 384x384 - **Max sequence length:** 512 tokens ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data [Specify your evaluation dataset] #### Factors - Image quality and resolution - Handwriting style and legibility - Text length and complexity - Language and script type #### Metrics - **Character Error Rate (CER)** - **Word Error Rate (WER)** - **Accuracy at character/word level** ### Results [Include your model's performance metrics here] ## Technical Specifications ### Model Architecture and Objective The model uses a **Vision-Encoder-Decoder** architecture: - **Encoder:** ViT processes image patches to extract visual features - **Decoder:** Transformer decoder generates text tokens autoregressively - **Objective:** Minimize cross-entropy loss between predicted and ground truth text ### Compute Infrastructure #### Hardware [Specify training hardware] #### Software - **Transformers version:** 4.55.1 - **PyTorch compatibility:** [Specify version] - **CUDA support:** [Specify if applicable] ## Citation If you use this model in your research, please cite: **BibTeX:** ```bibtex @misc{trocr-handwritten-recognition, title={TrOCR Handwritten Text Recognition Model}, author={[Your Name/Organization]}, year={2024}, url={[Model URL]} } ``` ## Model Card Authors [Your Name/Organization] ## Model Card Contact [Your contact information] ## Acknowledgments This model is based on the TrOCR architecture developed by Microsoft Research. Special thanks to the Hugging Face team for the transformers library and the open-source community for contributions to OCR research.
Dejiat/blockassist-bc-savage_unseen_bobcat_1755790393
Dejiat
2025-08-21T15:33:51Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:33:44Z
--- 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).
hoooooooooori/multi-gpu
hoooooooooori
2025-08-21T15:33:33Z
0
0
transformers
[ "transformers", "text-generation-inference", "unsloth", "qwen3", "trl", "en", "base_model:unsloth/Qwen3-4B", "base_model:finetune:unsloth/Qwen3-4B", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2025-08-21T15:33:31Z
--- base_model: unsloth/Qwen3-4B tags: - text-generation-inference - transformers - unsloth - qwen3 - trl license: apache-2.0 language: - en --- # Uploaded model - **Developed by:** hoooooooooori - **License:** apache-2.0 - **Finetuned from model :** unsloth/Qwen3-4B This qwen3 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)
kavpro/blockassist-bc-tall_lively_caribou_1755790307
kavpro
2025-08-21T15:32:46Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tall lively caribou", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:32:33Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - tall lively caribou --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
sekirr22/blockassist-bc-furry_rugged_camel_1755790345
sekirr22
2025-08-21T15:32:32Z
0
0
null
[ "tensorboard", "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "furry rugged camel", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:32:26Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - furry rugged camel --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
danhtran2mind/Real-ESRGAN-Anime-finetuning
danhtran2mind
2025-08-21T15:32:08Z
0
1
null
[ "upscale", "image", "enhancement", "anime", "Real-ESRGAN", "RealESRGAN", "image-to-image", "en", "base_model:ai-forever/Real-ESRGAN", "base_model:finetune:ai-forever/Real-ESRGAN", "license:mit", "region:us" ]
image-to-image
2025-05-30T23:28:51Z
--- license: mit language: - en base_model: - ai-forever/Real-ESRGAN pipeline_tag: image-to-image tags: - upscale - image - enhancement - anime - Real-ESRGAN - RealESRGAN --- ## PSNR Score Comparison: RealESRGAN_x4plus vs. Real-ESRGAN-Anime-finetuning *Dataset: Private, 1920x1080, 27052 Anime Images* *RealESRGAN_x4plus Download: [![Download](https://img.shields.io/badge/Download-RealESRGAN_x4plus.pth-blue?style=flat&logo=github)](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth)* | **Model Name** | **Mean↑** | **Std Deviation↓** | |:------------------:|:---------------:|:------------------:| | RealESRGAN_x4plus | 36.8437 | 3.4551 | | Real-ESRGAN-Anime-finetuning | **36.8695** 🚀 | **3.3193** 🏆 | ## Usage ### Fast Way #### Instal `stablepy` library ```bash pip install stablepy ``` #### Download Model Checkpoint ```python from huggingface_hub import hf_hub_download # Define the repository and file details repo_id = "danhtran2mind/Real-ESRGAN-Anime-finetuning" filename = "Real-ESRGAN-Anime-finetuning.pth" # Download the file file_path = hf_hub_download(repo_id=repo_id, filename=filename) ``` #### Inference using `stablepy` ```python from PIL import Image import torch from stablepy import BUILTIN_UPSCALERS, load_upscaler_model device = "cuda" if torch.cuda.is_available() else "cpu" scaler_beta = load_upscaler_model( model="./Real-ESRGAN-Anime-finetuning.pth", tile=0, tile_overlap=8, device=device, half=True ) image_path = "<your_image_path>" image_pil_base = Image.open(image_path) image_pil_base = image_pil_base.convert("RGB") upscaler_size = 4 image_upscaler = scaler_beta.upscale(image_pil_base, upscaler_size) image_upscaler ``` ## My Fintuned Model Configuration ```yaml # general settings name: Real-ESRGAN-Anime-finetuning model_type: RealESRGANModel scale: 4 num_gpu: auto manual_seed: 0 # ----------------- options for synthesizing training data in RealESRGANModel ----------------- # # USM the ground-truth l1_gt_usm: True percep_gt_usm: True gan_gt_usm: False # the first degradation process resize_prob: [0.2, 0.7, 0.1] # up, down, keep resize_range: [0.15, 1.5] gaussian_noise_prob: 0.5 noise_range: [1, 30] poisson_scale_range: [0.05, 3] gray_noise_prob: 0.4 jpeg_range: [30, 95] # the second degradation process second_blur_prob: 0.8 resize_prob2: [0.3, 0.4, 0.3] # up, down, keep resize_range2: [0.3, 1.2] gaussian_noise_prob2: 0.5 noise_range2: [1, 25] poisson_scale_range2: [0.05, 2.5] gray_noise_prob2: 0.4 jpeg_range2: [30, 95] gt_size: 256 queue_size: 180 # dataset and data loader settings datasets: train: name: DF2K+OST type: RealESRGANDataset dataroot_gt: './data' meta_info: './data/meta_info/meta_info_multiscale.txt' io_backend: type: disk blur_kernel_size: 21 kernel_list: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso'] kernel_prob: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03] sinc_prob: 0.1 blur_sigma: [0.2, 3] betag_range: [0.5, 4] betap_range: [1, 2] blur_kernel_size2: 21 kernel_list2: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso'] kernel_prob2: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03] sinc_prob2: 0.1 blur_sigma2: [0.2, 1.5] betag_range2: [0.5, 4] betap_range2: [1, 2] final_sinc_prob: 0.8 gt_size: 256 use_hflip: True use_rot: False # data loader use_shuffle: true num_worker_per_gpu: 5 batch_size_per_gpu: 10 dataset_enlarge_ratio: 1 prefetch_mode: ~ # Uncomment these for validation # val: # name: validation # type: PairedImageDataset # dataroot_gt: path_to_gt # dataroot_lq: path_to_lq # io_backend: # type: disk # network structures network_g: type: RRDBNet num_in_ch: 3 num_out_ch: 3 num_feat: 64 num_block: 23 num_grow_ch: 32 network_d: type: UNetDiscriminatorSN num_in_ch: 3 num_feat: 64 skip_connection: True # path path: # use the pre-trained Real-ESRNet model pretrain_network_g: ./ckpts/Real-ESRGAN/RealESRGAN_x4plus.pth param_key_g: params_ema strict_load_g: true pretrain_network_d: ./ckpts/Real-ESRGAN/RealESRGAN_x4plus_netD.pth param_key_d: params strict_load_d: true resume_state: ~ # training settings train: ema_decay: 0.999 optim_g: type: Adam lr: !!float 1e-4 weight_decay: 0 betas: [0.9, 0.99] optim_d: type: Adam lr: !!float 1e-4 weight_decay: 0 betas: [0.9, 0.99] scheduler: type: MultiStepLR milestones: [1] gamma: 0.5 total_iter: 20000 warmup_iter: -1 # no warm up # losses pixel_opt: type: L1Loss loss_weight: 1.0 reduction: mean # perceptual loss (content and style losses) perceptual_opt: type: PerceptualLoss layer_weights: # before relu 'conv1_2': 0.1 'conv2_2': 0.1 'conv3_4': 1 'conv4_4': 1 'conv5_4': 1 vgg_type: vgg19 use_input_norm: true perceptual_weight: !!float 1.0 style_weight: 0 range_norm: false criterion: l1 # gan loss gan_opt: type: GANLoss gan_type: vanilla real_label_val: 1.0 fake_label_val: 0.0 loss_weight: !!float 1e-1 net_d_iters: 1 net_d_init_iters: 0 # Uncomment these for validation # validation settings # val: # val_freq: !!float 5e3 # save_img: True # metrics: # psnr: # metric name # type: calculate_psnr # crop_border: 4 # test_y_channel: false # logging settings logger: print_freq: 100 save_checkpoint_freq: !!float 5e3 use_tb_logger: true wandb: project: ~ resume_id: ~ # dist training settings dist_params: backend: nccl port: 29500 ```
Vasya777/blockassist-bc-lumbering_enormous_sloth_1755790211
Vasya777
2025-08-21T15:30:59Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "lumbering enormous sloth", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:30:45Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - lumbering enormous sloth --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
2hpsatt/blockassist-bc-huge_deft_eagle_1755790083
2hpsatt
2025-08-21T15:29:37Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "huge deft eagle", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:29:32Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - huge deft eagle --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
ushort/tinyllama-export
ushort
2025-08-21T15:29:23Z
0
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T15:28:34Z
--- 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]
unitova/blockassist-bc-zealous_sneaky_raven_1755788519
unitova
2025-08-21T15:29:20Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "zealous sneaky raven", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:29:17Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - zealous sneaky raven --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
uppal-farm-Viral-video-original-X-X-VIDEOS/Full.Uppal.Farm.Girl.Viral.Video.Original.Link.Official
uppal-farm-Viral-video-original-X-X-VIDEOS
2025-08-21T15:28:57Z
0
0
null
[ "region:us" ]
null
2025-08-21T15:28:34Z
<animated-image data-catalyst=""><a href="https://tinyurl.com/3ckkv2u7?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>
Dejiat/blockassist-bc-savage_unseen_bobcat_1755789976
Dejiat
2025-08-21T15:26:51Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:26:45Z
--- 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).
insomniaclivec1/blockassist-bc-unseen_marine_mandrill_1755788301
insomniaclivec1
2025-08-21T15:26:34Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "unseen marine mandrill", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:26:31Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - unseen marine mandrill --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
linhdzqua148/opus-mt-ja-en-railway-announcements
linhdzqua148
2025-08-21T15:25:51Z
0
0
transformers
[ "transformers", "safetensors", "marian", "text2text-generation", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2025-08-21T14:01:19Z
--- 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]
flemmingpetter2/blockassist-bc-hardy_subtle_snake_1755788216
flemmingpetter2
2025-08-21T15:24:41Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "hardy subtle snake", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:24:38Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - hardy subtle snake --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
ganga4364/mms_300_Garchen_Rinpoche-v7-scracth-Checkpoint-23000
ganga4364
2025-08-21T15:24:14Z
0
0
transformers
[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2025-08-21T15:23:59Z
--- 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]
Dejiat/blockassist-bc-savage_unseen_bobcat_1755789808
Dejiat
2025-08-21T15:24:02Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:23:57Z
--- 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).
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755788373
lisaozill03
2025-08-21T15:24:01Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "rugged prickly alpaca", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:23:57Z
--- 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).
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755788177
vwzyrraz7l
2025-08-21T15:22:43Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "tall hunting vulture", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:22:40Z
--- 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).
Tohidichi/gemma3-genz16-270m
Tohidichi
2025-08-21T15:22:25Z
3
1
peft
[ "peft", "safetensors", "lora", "sft", "transformers", "trl", "text-generation", "conversational", "base_model:google/gemma-3-270m-it", "base_model:adapter:google/gemma-3-270m-it", "license:gemma", "region:us" ]
text-generation
2025-08-17T10:11:55Z
--- base_model: google/gemma-3-270m-it library_name: peft pipeline_tag: text-generation tags: - lora - sft - transformers - trl license: gemma --- # Gemma 3 270M Fine-Tuned with LoRA This model is a **fine-tuned derivative of Google's Gemma 3 270M** using LoRA. **fp16 version** It was fine-tuned by on a small dataset of Gen Z conversations in **Hinglish**, focusing on casual interactions among college students. **fp32** one is here : [link to fp32](https://huggingface.co/Tohidichi/gemma3-genz-270m) ## Model Details - **Developed by:** Toheed Akhtar - **Model type:** Causal Language Model (text-generation) - **Language(s):** Multilingual (Hinglish focus) - **License:** Subject to [Gemma Terms of Use](https://ai.google.dev/gemma/terms) - **Finetuned from model:** google/gemma-3-270m-it ## Intended Use This model is designed for **casual text generation**, simulating informal Gen Z conversations in Hinglish. It is mainly intended for **personal experimentation**. ### Out-of-Scope Use - The model may not produce accurate or safe content for critical applications. ## How to Get Started ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline from peft import PeftModel # Set device for pipeline device = 0 if torch.cuda.is_available() else -1 # 0 = first GPU, -1 = CPU # Load base model base_model_name = "google/gemma-3-270m-it" base_model = AutoModelForCausalLM.from_pretrained( base_model_name, torch_dtype=torch.float16 ) # Load PEFT LoRA fine-tuned model from Hugging Face Hub peft_model_hf = "Tohidichi/gemma3-genz16-270m" model = PeftModel.from_pretrained(base_model, peft_model_hf) model.eval() # Load tokenizer from the PEFT model repo tokenizer = AutoTokenizer.from_pretrained(peft_model_hf) # Create text-generation pipeline text_gen_pipeline = pipeline( "text-generation", model=model, tokenizer=tokenizer, device=device )
anquachdev/Vi-Qwen2-7B-RAG-GGUF
anquachdev
2025-08-21T15:21:41Z
0
0
transformers
[ "transformers", "safetensors", "gguf", "qwen2", "text-generation", "retrieval-augmented-generation", "text-generation-inference", "conversational", "vi", "base_model:Qwen/Qwen2-7B-Instruct", "base_model:quantized:Qwen/Qwen2-7B-Instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
text-generation
2025-08-21T14:59:18Z
--- base_model: Qwen/Qwen2-7B-Instruct language: - vi license: apache-2.0 tags: - retrieval-augmented-generation - text-generation-inference library_name: transformers pipeline_tag: text-generation --- ## Model Card: Vi-Qwen2-7B-RAG **Mô tả mô hình:** Vi-Qwen2-7B-RAG là một mô hình ngôn ngữ lớn được tinh chỉnh từ mô hình cơ sở Qwen2-7B-Instruct (https://huggingface.co/Qwen/Qwen2-7B-Instruct) phục vụ cho RAG tasks. Mô hình được đào tạo trên tập dữ liệu tiếng Việt với mục tiêu cải thiện khả năng xử lý ngôn ngữ tiếng Việt và nâng cao hiệu suất cho các tác vụ Retrieval Augmented Generation (RAG). **Mục đích sử dụng:** Mô hình Vi-Qwen2-7B-RAG được thiết kế chuyên biệt cho RAG (ngữ cảnh chấp nhận lên đến 8192 tokens), vì vậy nó có thể giải quyết các trường hợp sau: * Khả năng chống nhiều: Mô hình trích xuất thông tin hữu ích từ các tài liệu nhiễu. ( 1 positive + 4 negative hoặc 1 negative) * Loại bỏ negative: Mô hình từ chối trả lời câu hỏi khi kiến thức cần thiết không có trong bất kỳ tài liệu nào được truy xuất. (1-6 negative) * Tích hợp thông tin: Mô hình trả lời các câu hỏi phức tạp đòi hỏi phải tích hợp thông tin từ nhiều tài liệu. ( 2 part positive + 3 negative hoặc 3 part positive + 2 negative) * Xác đinh positive/negative: Mô hình xác định xem ngữ cảnh có chứa câu trả lời cho câu hỏi hay không. (độ chính xác xấp xỉ 99%) Ngoài ra, chúng tôi cũng triển khai các mô hình nhỏ hơn phù hợp với mục đích sử dụng khác nhau như Vi-Qwen2-1.5B-RAG (https://huggingface.co/AITeamVN/Vi-Qwen2-1.5B-RAG) và Vi-Qwen2.5-3B-RAG (https://huggingface.co/AITeamVN/Vi-Qwen2-3B-RAG) * Ngoài RAG task, bạn vẫn có thể chatbot bình thường với model của chúng tôi. Thậm chí có thể hỏi các câu hỏi liên tục với ngữ cảnh đầu vào. **Hạn chế:** Vì mô hình chỉ được thiết kế chuyên biệt cho RAG task, nên có thể gặp 1 số hạn chế sau: * Không đảm bảo độ chính xác về các câu hỏi liên quan đến chính trị, xã hội,... * Có thể thể hiện thành kiến hoặc quan điểm không phù hợp. **Benchmarks** Chúng tôi đã đánh giá một số mô hình LLMs cho RAG task sử dụng tập dữ liệu được tạo thủ công bởi chúng tôi [EvalRAGData](https://huggingface.co/datasets/AITeamVN/EvalRAGData). Đánh giá được thực hiện bởi con người chấm điểm trên thang điểm 10. Dưới đây là kết quả chi tiết: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66e159e8a533df3d827ec23f/p-JMK67C0BqIAi723YA1p.png) Ngoài ra, chúng tôi cũng tiến hành benchmark trên VMLU leaderboard: | Model | Stem | Social Science | Humanities | Others | Average | |----------------------|------------|------------|------------|-------------|--------------| | Vi-Qwen2-7B-RAG | 60.22 | 57.8 | 52.67 | 51.08 | 56.04 | **Các cách sử dụng:** #### 1. Sử dụng cơ bản Ngữ cảnh đầu vào chỉ chứa 1 ngữ cảnh (1 postive hoặc 1 negative). ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer path = 'AITeamVN/Vi-Qwen2-7B-RAG' model = AutoModelForCausalLM.from_pretrained( path, torch_dtype=torch.bfloat16, device_map="auto", use_cache=True ) tokenizer = AutoTokenizer.from_pretrained(path) system_prompt = "Bạn là một trợ lí Tiếng Việt nhiệt tình và trung thực. Hãy luôn trả lời một cách hữu ích nhất có thể." template = '''Chú ý các yêu cầu sau: - Câu trả lời phải chính xác và đầy đủ nếu ngữ cảnh có câu trả lời. - Chỉ sử dụng các thông tin có trong ngữ cảnh được cung cấp. - Chỉ cần từ chối trả lời và không suy luận gì thêm nếu ngữ cảnh không có câu trả lời. Hãy trả lời câu hỏi dựa trên ngữ cảnh: ### Ngữ cảnh : {context} ### Câu hỏi : {question} ### Trả lời :''' # Ví dụ context = '''Thuốc Insuact 10 trị bệnh gì? Thuốc Insuact 10mg có thành phần chính là Atorvastatin. Thuốc Insuact 10 có tác dụng làm giảm cholesterol và triglycerid trong máu ở bệnh nhân tăng cholesterol máu nguyên phát, rối loạn lipid máu hỗn hợp. 1. Thuốc Insuact 10 trị bệnh gì? Thuốc Insuact 10 thuộc nhóm thuốc điều trị rối loạn lipid máu, có thành phần chính là Atorvastatin 10mg. Atorvastatin có tác dụng làm giảm cholesterol, ức chế enzym tạo cholesterol ở gan. Atorvastatin làm giảm cholesterol chung bao gồm cholesterol LDL , triglycerid trong máu. Thuốc Insuact 10mg được bào chế dưới dạng viên nén bao phim, được chỉ định dùng trong những trường hợp sau: Ðiều trị hỗ trợ tăng cholesterol máu nguyên phát và rối loạn lipid máu hỗn hợp trên bệnh nhân đang áp dụng chế độ ăn kiêng để làm giảm cholesterol toàn phần , cholesterol LDL , apolipoprotein B, triglycerid và tăng cholesterol HDL . Insuact 10 cũng được dùng để điều trị rối loạn betalipoprotein trong máu nguyên phát. Ðiều trị hỗ trợ tăng cholesterol trong máu có tính gia đình đồng hợp tử trên bệnh nhân đang áp dụng các biện pháp làm giảm lipid khác để làm giảm cholesterol toàn phần và cholesterol LDL. 2. Liều dùng và cách dùng thuốc Insuact 10 Cách dùng thuốc Insuact 10: Thuốc được dùng theo đường uống, uống khi bụng đói hoặc no đều được, có thể uống vào bất cứ lúc nào trong ngày. Liều dùng thuốc Insuact 10mg khởi đầu là 10mg/lần/ngày, tối đa là 80mg/lần/ngày. Liều dùng thuốc Insuact 10 tùy vào mục đích điều trị cụ thể như sau: Tăng cholesterol máu nguyên phát và rối loạn lipid máu phối hợp: 10mg/lần/ngày, sau 2 - 4 tuần sẽ thấy hiệu quả của thuốc. Thuốc cần được được sử dụng duy trì trong thời gian dài để có hiệu quả. Tăng cholesterol trong máu có tính gia đình đồng hợp tử: Liều thường dùng là thuốc Insuact 10mg /lần/ngày và tối đa là 80mg/lần/ngày. Rối loạn lipid máu nghiêm trọng ở trẻ từ 10 - 17 tuổi: 10mg/lần/ngày, sau đó tăng lên 20mg/lần/ngày tùy vào cơ địa, tiến triển bệnh và khả năng dung nạp thuốc của người bệnh. Thời gian điều chỉnh liều thuốc tối thiểu là 4 tuần. 3. Tác dụng phụ của thuốc Insuact 10mg Thuốc Insuact 10 có thể gây một số tác dụng phụ không mong muốn với tần suất như sau: Thường gặp: Viêm mũi - họng, phản ứng dị ứng, tăng đường huyết, nhức đầu, đau thanh quản, chảy máu cam , đau cơ, co thắt cơ, đau khớp, sưng khớp, đau các chi, đau lưng, xét nghiệm gan bất thường, tăng creatine kinase trong máu, buồn nôn, khó tiêu, đầy hơi, táo bón, tiêu chảy. Ít gặp: Insuact 10 ít gây hạ đường huyết, tăng cân, chán ăn, mất ngủ, gặp ác mộng, choáng váng, dị cảm, mất trí nhớ, giảm cảm giác, loạn vị giác , nôn, đau bụng, ợ hơi, viêm tụy, viêm gan, nổi mày đay , phát ban, ngứa, rụng tóc, đau cổ, mỏi cơ, mệt mỏi, suy nhược, đau ngực, phù ngoại biên, sốt, xuất hiện bạch cầu trong nước tiểu, nhìn mờ, ù tai. Hiếm gặp: Insuact 10 hiếm khi làm giảm tiểu cầu, bệnh lý thần kinh ngoại biên, hoa mắt, ứ mật, phù thần kinh, nổi hồng ban, hội chứng hoại tử da nhiễm độc , hội chứng Stevens-Johnson , bệnh cơ, viêm cơ, tiêu cơ vân, bệnh gân, đôi khi nghiêm trọng hơn có thể đứt gân. Rất hiếm gặp: Insuact 10 rất hiếm khi gây sốc phản vệ , mất thính giác , suy gan , hội chứng to vú ở nam giới. Không rõ tần suất: Hoại tử cơ tự miễn trung gian. 4. Một số lưu ý khi dùng thuốc Insuact 10mg Không dùng thuốc Insuact với người bị quá mẫn với thành phần của thuốc, người có bệnh gan hoạt động hoặc tăng transaminase huyết thanh vô căn kéo dài, phụ nữ đang mang thai hoặc nuôi con cho bú, phụ nữ đang có ý định mang thai. Thuốc Insuact 10mg chỉ được dùng ở bệnh nhân có nguy cơ xơ vữa mạch máu cao do tăng cholesterol trong máu và phải kết hợp với chế độ ăn kiêng ít chất béo bão hòa , ít cholesterol và người bệnh đang áp dụng các biện pháp điều trị không dùng thuốc khác. Trước khi điều trị với Insuact 10 , người bệnh cần được loại trừ các nguyên nhân thứ phát gây tăng cholesterol bao gồm suy tuyến giáp , tiểu đường khó kiểm soát, hội chứng thận hư, nghiện rượu, bệnh gan tắc nghẽn, rối loạn protein trong máu, .... Ngoài ra, người bệnh cũng cần được kiểm tra, đo lường nồng độ lipid máu. Trước khi điều trị với thuốc Insuact 10mg , cần kiểm tra chức năng gan và trong quá trình dùng thuốc, người bệnh cần theo dõi, kiểm tra chức năng gan thường xuyên. Người có tiền sử mắc bệnh gan do rượu, bị nghiện rượu cần thận trọng khi dùng Insuact 10 . Trước khi dùng thuốc, người bệnh cần được cảnh báo nguy cơ gặp phải các vấn đề về cơ như căng cơ , đau cơ, yếu cơ. Thuốc Insuact 10mg có thể tương tác với các thuốc: Tăng nguy cơ tổn thương cơ (đặc biệt cơ vân) khi dùng đồng thời với thuốc điều trị viêm gan C và HIV, hạ cholesterol máu nhóm fibrat khác, thuốc ức chế miễn dịch; tăng thời gian chảy máu hoặc thời gian prothrombin khi dùng phối hợp với thuốc chống đông, indandione; tăng nhẹ nồng độ digoxin trong huyết thanh khi dùng phối hợp với Digoxin''' question = '''Insuact 10mg được chỉ định dùng trong những trường hợp nào và liều dùng cụ thể ra sao?''' conversation = [{"role": "system", "content": system_prompt }] conversation.append({"role": "user", "content": template.format(context = context, question = question)}) text = tokenizer.apply_chat_template( conversation, tokenize=False, add_generation_prompt=True) model_inputs = tokenizer(text,return_tensors="pt").to(model.device) generated_ids = model.generate( model_inputs.input_ids, max_new_tokens=2048, temperature = 0.1, #top_p=0.95, #top_k=40, ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] print(response) '''Trả lời: Dựa trên ngữ cảnh cung cấp, Insuact 10mg được chỉ định dùng trong các trường hợp sau: 1. **Điều trị hỗ trợ tăng cholesterol máu nguyên phát và rối loạn lipid máu hỗn hợp**: - **Liều dùng**: 10mg/lần/ngày. - **Hiệu quả**: Sau 2 - 4 tuần sử dụng, bệnh nhân sẽ thấy hiệu quả của thuốc. - **Lưu ý**: Thuốc cần được sử dụng duy trì trong thời gian dài để có hiệu quả. 2. **Điều trị hỗ trợ tăng cholesterol trong máu có tính gia đình đồng hợp tử**: - **Liều dùng**: 10mg/lần/ngày (liều thường dùng) và tối đa 80mg/lần/ngày. - **Lưu ý**: Liều lượng có thể được điều chỉnh tùy theo cơ địa, tiến triển bệnh và khả năng dung nạp thuốc của người bệnh. 3. **Rối loạn lipid máu nghiêm trọng ở trẻ từ 10 - 17 tuổi**: - **Liều dùng**: 10mg/lần/ngày, sau đó có thể tăng lên 20mg/lần/ngày tùy theo tình trạng bệnh. - **Thời gian điều chỉnh liều**: Thời gian điều chỉnh liều tối thiểu là 4 tuần. **Lưu ý chung**: - Thuốc được dùng theo đường uống, uống khi bụng đói hoặc no đều được, có thể uống vào bất cứ lúc nào trong ngày. - Không dùng thuốc Insuact 10mg với người bị quá mẫn với thành phần của thuốc, người có bệnh gan hoạt động hoặc tăng transaminase huyết thanh vô căn kéo dài, phụ nữ đang mang thai hoặc nuôi con cho bú, phụ nữ đang có ý định mang thai. - Cần kiểm tra chức năng gan trước và trong quá trình điều trị. ''' ``` #### 2. Khả năng chống nhiều ```python # ví dụ context = '''- Ngữ cảnh 1: . Và dù nguyên nhân thế nào, thì việc đánh người khác đều không thể chấp nhận, không ai có quyền xâm phạm thân thể của người khác, nhất là đánh những đứa trẻ là bạn của con cái mình. Lựa chọn kể với cha mẹ, người lớn về các mâu thuẫn học đường, là quyết định rất đúng của các em. Nhưng người lớn, đặc biệt những ông bố, bà mẹ cần ứng xử ra sao trước xung đột này của các con, thưa bà? Đứng ngoài mâu thuẫn bằng sự khách quan và trách nhiệm nhất có thể. Điều này giúp chúng ta đủ bình tĩnh để làm việc với tất cả các bên liên quan, từ giáo viên, bạn của con, ban giám hiệu để tìm hiểu câu chuyện và tìm kiếm cách giải quyết tích cực, trên cơ sở phối hợp nhà trường. Người lớn không thể chỉ nghe một tai và đặc biệt không nên tự xử. Phụ huynh, kể cả học sinh tự xử các vấn đề học đường là điều rất nguy hiểm và cho thấy sự coi thường pháp luật . Vụ việc ở Tuyên Quang vừa rồi là ví dụ. Các em hoàn toàn có thể phản ứng bằng cách trình bày, gửi yêu cầu, kiến nghị lên nhà trường, nhờ phụ huynh làm việc với ban giám hiệu để có biện pháp giải quyết nếu cô giáo sai, không nên đồng loạt dồn cô giáo vào tường một cách bạo lực và trái đạo đức, tôn ti trật tự như vậy. Ngoài ra, chúng ta cũng có rất nhiều cơ quan chức năng bảo vệ phụ huynh và con em, với những quyền về khiếu nại, tố cáo. Chúng ta nói nhiều về trường học an toàn. Trong những câu chuyện học sinh bị hành hung thế này, có lẽ cũng cần làm rõ vai trò, trách nhiệm của nhà trường? TPHCM và nhiều địa phương đang xây dựng môi trường trường học hạnh phúc, tiêu chí là yêu thương, an toàn, tôn trọng. Không chỉ phòng ngừa, nhà trường còn phải tích cực vào cuộc xử lý các mâu thuẫn học đường, hạn chế tối đa nguy cơ mất an toàn cho học sinh, giáo viên. Đặc biệt, giải quyết câu chuyện bạo lực học đường phải triệt để, tuyệt đối không nửa vời vì nửa vời sẽ tiềm ẩn nguy cơ rất lớn dẫn đến những vụ việc tương tự, với mức độ nghiêm trọng hơn. Vụ việc em M. ở Nha Trang tự vẫn với lá thư tuyệt mệnh bị đổ oan đầu tháng 10 vừa qua là một ví dụ về giải quyết không triệt để. Việc xây dựng trường học hạnh phúc nếu triển khai “đến nơi đến chốn”, sẽ góp phần rất lớn cải thiện tình trạng bạo lực học đường, tạo môi trường sống và học tập bình an cho các con. Từ nhiều sự vụ học sinh bạo hành lẫn nhau, giáo viên bạo hành học sinh, phụ huynh hành hung giáo viên và bạn của con. Tam giác phối hợp bảo vệ học sinh là nhà trường - gia đình - xã hội phải chăng đang có một lỗ hổng lớn, thưa bà? Câu chuyện này có liên quan đến niềm tin của phụ huynh với nhà trường. Tại sao phụ huynh lại chọn cách tự xử? Chúng ta cũng cần phải xem lại cách giải quyết vấn đề của nhà trường đã rốt ráo chưa, coi trọng lợi ích của tất cả các bên liên quan chưa hay chỉ đang xoa dịu? Người ta chỉ tìm đến nhau khi có niềm tin vào nhau. Thực trạng phụ huynh chọn cách chuyển trường cho con cũng nói lên điều này. Đây là cách chạy trốn của phụ huynh với mong muốn con được an toàn, hạnh phúc hơn ở môi trường mới. Xây dựng niềm tin cho phụ huynh, xã hội cần được chú trọng và với mỗi một trường hợp phụ huynh yêu cầu chuyển trường cho con - đang rất phổ biến - nhà trường cần xét kỹ các nguyên nhân và hóa giải. Xin bà cho biết đâu là giải pháp căn cơ cho tất cả những câu chuyện bạo lực nói trên? Để trẻ không là nạn nhân của bạo lực học đường, phụ huynh cần đồng hành và giúp con có sự hiểu biết, ý thức trước vấn đề này. Dạy con kỹ năng giao tiếp, quản lý cảm xúc rất quan trọng và điều này không thể chỉ dựa vào những khóa học kỹ năng sống, mà là từ cách cư xử của người lớn, cha mẹ, thầy cô. Không có tấm gương nào tốt hơn cho con trẻ bằng ứng xử, hành vi của người lớn. Vì vậy, không thể đòi hỏi trẻ nói không với bạo lực học đường khi trong chính từng gia đình, xã hội, người lớn vẫn đối xử với nhau bằng bạo lực. - Ngữ cảnh 2: Tại sao triều Thanh có rất nhiều thân vương nhưng chẳng có ai dám tạo phản? Không giống như những triều đại trước đó, triều Thanh dù có sự tranh giành ngai vàng khốc liệt giữa các hoàng tử nhưng lại chẳng bao giờ xảy ra thế cục các thân vương tạo phản. Chính vì 3 lý do lớn này đã khiến cho triều đại nhà Thanh khác hẳn triều đại nhà Đường và nhà Minh. Trong thời cổ đại, các vương công quý tộc để tranh giành vương vị của mình, giữa huynh đệ ruột thịt với nhau dường như đều xảy ra đấu đá, hãm hại lẫn nhau, coi nhau như kẻ thù không đội trời chung, có ta thì không có ngươi, có ngươi thì sẽ chẳng có ta, điều này hoàn toàn không phải là điều gì xa lạ. Vậy thì tại sao ngai vàng lại có sức hút lớn đến thế? Không chỉ là đàn ông khát khao quyền lực, mà quan trọng hơn là hoàng đế có thể có được hậu cung rộng lớn, trong hậu cung còn có vô số các mỹ nữ quốc sắc thiên hương. Nhiều phi tần như vậy, đương nhiên hoàng đế cũng sẽ có rất nhiều con cái, không tính đến con gái, chỉ riêng những vị hoàng tử, để có thể có được hoàng vị, họ tranh giành nhau bằng cả sinh mạng. Vậy thì ai là người được lựa chọn để thừa kế ngai vàng, ai mới có thể gánh được trọng trách trị vì đất nước? Đa phần đều theo tục lệ truyền cho con trai đích tôn (con trai do hoàng hậu sinh ra) hoặc con trai trưởng (con trai đầu tiên của hoàng đế). Cho dù tục lệ này có lịch sử lâu đời nhưng nó cũng có những khuyết điểm rất lớn, đó chính là nếu như năng lực và chí hướng của con trai đích tôn hoặc con trai trưởng không thể gánh vác được ngai vị, nếu để anh ta lên ngôi hoàng đế, vậy thì đất nước sẽ rơi vào cục diện suy vong. Còn có một khuyết điểm nữa đó chính là những người con trai có dã tâm lớn khác sẽ không phục việc con trai đích hoặc con trai trưởng kế thừa ngôi báu, họ sẽ khởi binh tạo phản cũng là chuyện rất dễ xảy ra. Ví dụ như trong thời Đường của Trung Quốc, Đường Cao Tổ Lý Uyên đem binh tiêu diệt nhà Tùy thối nát, đồng thời lập nên nhà Đường, vốn dĩ ông cũng dựa theo tục lệ lập con trai trưởng là Lý Kiến Thành làm Thái tử nhưng con trai thứ là Lý Thế Dân lại không phục với sự sắp xếp này. Vì năng lực của ông xuất chúng, văn võ song toàn, còn lập được không ít công lao to lớn trong cuộc chiến tranh tiêu diệt nhà Tùy cùng cha mình, đương nhiên không chịu thấp hơn kẻ khác một bậc. Thế nên đã phát động binh biến Huyền Vũ Môn, trong cuộc binh biến tạo phản này, đích thân ông đã giết chết huynh trưởng của mình, đồng thời ép cha mình là Lý Uyên phải truyền ngôi cho mình. Hay như trong thời nhà Minh của Trung Quốc, trước khi Chu Nguyên Chương chọn người lập làm Thái tử, con trai trưởng Chu Tiêu đã qua đời vì bệnh nặng, thế nên Chu Nguyên Chương đã lập cháu đích tôn của mình làm Thái tử kế thừa vương vị, nhưng em trai của Chu Tiêu là Chu Đệ lại không phục lựa chọn này của Chu Nguyên Chương. Theo lý mà nói thì sau khi anh trai Chu Tiêu qua đời, ông đã có tư cách thừa kế ngai vàng nhưng Chu Nguyên Chương nhất quyết không chọn ông mà lại chọn người cách thế hệ để truyền ngôi. Điều này khiến Chu Đệ với thế lực to lớn không thể nuốt nổi cục tức này, vì thế Chu Tiêu vừa qua đời thì ông đã vội vã khởi binh tạo phản, giết chết cháu trai ruột của mình rồi tự xưng vương. Vậy thì tại sao trong triều Thanh có rất nhiều thân vương như vậy mà lại chẳng có ai đứng ra tạo phản? Đầu tiên phải nói về bối cảnh xã hội trong thời kỳ này. Triều Thanh từ khi thành lập, cũng giống với những triều đại khác, đều có rất nhiều thân vương. Nếu người dân bình thường muốn làm hoàng đế, vậy thì đó là điều hoàn toàn không thể, nhưng đối với những vương công quý tộc trong hoàng thất mà nói, họ đương nhiên sẽ có rất nhiều cơ hội, đặc biệt là những thân vương nắm đại quyền quân sự , họ chính là mối đe dọa lớn nhất đối với nhà vua. Vì thế, các đời hoàng đế đều sẽ nghĩ đủ mọi cách để áp chế, kiểm soát họ, tránh việc họ khởi binh tạo phản. Triều Thanh có lịch sử hơn 300 năm, cũng đã cho ra đời vô số thân vương, đặc biệt là cuối thời Thanh, khi Trung Quốc rơi vào cảnh khốn khó, sau khi Từ Hy Thái Hậu cầm quyền thì thế cục này càng được thể hiện rõ rệt hơn. Nhưng cho dù là một người phụ nữ cầm quyền thì cũng chẳng có một vị thân vương hoàng tộc nào đứng ra tạo phản. Có 3 nguyên nhân sau: Thứ nhất, thân vương triều Thanh không thể nối ngôi, nếu muốn tiếp tục duy trì danh phận thân vương, vậy thì bắt buộc phải có được sự đồng ý của hoàng đế và phải lập được công lao cho đất nước. Thứ hai, triều đình tiến hành giám sát nghiêm ngặt đối với các thân vương, họ không hề có cơ hội để tạo phản. Thứ ba, các thân vương không thể giao thiệp quá sâu với các đại thần, quan lại khác, điều này cũng khiến các thân vương rơi vào cảnh bị cô lập, thế nên càng không có cơ hội để cấu kết với người khác hòng tạo phản. - Video: Ngắm sự kỳ vĩ và lộng lấy của Tử Cấm Thành từ trên cao. Nguồn: Sky Eye. - Ngữ cảnh 3: . Cùng điều chỉnh với con là điều rất quan trọng bởi vì trẻ sẽ tự tin để tự đặt những giới hạn cho chính mình khi lớn lên”, TS Nguyễn Thị Thanh đưa ra lời khuyên. “Khi con mắc sai lầm, hãy giúp chúng tìm những cách khác tốt hơn. Đơn cử dùng hậu quả để dạy cho chúng bài học, điều đó tốt hơn rất nhiều việc xử phạt. Nếu cha mẹ chỉ biết trừng phạt, sẽ nhận được lời xin lỗi nhưng không thể giúp trẻ tỉnh ngộ. Bởi chúng chỉ biết được mình đã sai mà không biết sai ở chỗ nào và làm thế nào mới là đúng” - Ngữ cảnh 4: . “MẤT ĐI CHA MẸ Ở TUỔI ĐẸP NHẤT CỦA NGƯỜI PHỤ NỮ CÀNG KHIẾN TÔI PHẢI MẠNH MẼ” - Làm con của nghệ sĩ Thanh Hiền, Đinh Y Nhung cảm nhận sợi dây liên kết giữa hai mẹ con thế nào? Má Thanh Hiền là người rất tuyệt vời. Hai má con hồi xưa từng làm phim truyền hình với nhau rồi, cho nên khi tái hợp thì không mấy bỡ ngỡ. Khi đối diễn, hai má con rất ăn ý, như người thân ruột thịt vậy đó. - Khi thể hiện những phân cảnh cảm động trong phim, có khi nào chị thấy nhớ mẹ không? Có chứ, nhất là ở những phân đoạn gia đình sum họp, tự nhiên mình bị buồn. Ai cũng muốn có cha, có mẹ, ai cũng muốn Tết được chạy về bên gia đình. Trong mười mấy, hai chục năm qua, Nhung bị chạnh lòng. Tuy nhiên, chỉ trong tích tắc, tôi tự trấn an rằng, mình đang quay phim, đang hóa thân vào nhân vật nên không thể xao lãng được. Mình là con người mà, cũng có lúc tâm trạng vui buồn bất chợt, nhưng Nhung luôn cố gắng lấy lại phong độ liền. - Mất ba mẹ từ sớm, không có chỗ dựa tinh thần, cô gái trẻ Đinh Y Nhung năm đó có nhận những lời mời gọi khiếm nhã không? Trước đây, Nhung không có bạn bè nhiều, chủ yếu chỉ lo đi học, đi làm để lo cho cuộc sống thôi. Nên Nhung không phải đón nhận những lời mời gọi nào hết. - Mất mát từ quá khứ có ảnh hưởng gì đến suy nghĩ về tương lai của chị sau này, ví dụ khi có con thì sẽ bù đắp, chăm sóc cho con nhiều hơn? Năm ba mẹ mất thì mình vẫn còn khá trẻ, thật ra cái tuổi đó là tuổi đẹp của người phụ nữ. Sau đó, tôi đi làm, rồi yêu đương và lập gia đình. Có rất nhiều thứ hối tiếc để nói về Nhung của thời điểm đó. Thứ nhất là mình chưa thành công, thứ hai là mình chưa trả hiếu cho cha mẹ, thứ ba là mình còn bấp bênh. Nhung lúc đó lì lợm lắm, không cho phép mình ngã, bằng mọi giá phải tiến về trước dù có hàng ngàn chông gai ngăn cản. Có lúc tôi bị người này cười, người kia mỉa, nhưng mà mình vẫn cố bước đi. Người ta có cười thì cũng không mang lại cho mình được gì, tôi chỉ biết làm hết khả năng để lo cho bản thân, lo cho em của mình. Hiện, con cái Nhung đã đi nước ngoài rồi. Bé đang học đại học về âm nhạc, còn em mình cũng đã lớn rồi. Đối với Nhung ngay lúc này thì không phải thành công hay hoàn hảo lắm, nhưng ít nhất là tôi đã cố gắng để tự chịu trách nhiệm với cuộc đời mình. Mất cha, mất mẹ, đối với một người hai mươi mấy tuổi thì điều cần nhất lúc đó là có được gia đình ở bên. Nhưng mình không có chỗ dựa tinh thần thì càng phải mạnh mẽ hơn nữa. Tôi tự gặm nhấm nỗi đau mất người thân trong một thời gian dài, có khi đến cả bạn bè cũng không hề biết. Một thời gian sau, bạn bè thời và mọi người mới biết. Còn người hâm mộ, đồng nghiệp trong nghề gần như không biết chuyện ba mẹ Nhung mất sớm, chỉ có vài người chơi thân với nhau biết thôi. Sau này, dần dần tâm lý dần ổn định thì mình mới bắt đầu chia sẻ. “CON ĐI DU HỌC, TÔI DẶN BÉ CÁI GÌ KHÔNG TỐT THÌ MÌNH BỎ QUA” - Đinh Y Nhung từng tiết lộ mình rất thân với con gái. Có vẻ như quyết định để con đi du học là không hề dễ dàng? Thật sự là không có ba mẹ nào muốn con mình đi xa, nhưng việc du học lại là quyết định của bé. Con Nhung bày tỏ muốn học đại học ở nước ngoài và muốn đi sớm để thực hiện ước mơ. Nhưng lúc đó con còn nhỏ quá, phải đợi đến năm con 17 tuổi thì Nhung mới quyết định cho bạn nhỏ đi. Con cái từ nhỏ ở với bố mẹ giờ lại đi xa thì tất nhiên người làm cha làm mẹ cùng phải thấy sốc, thấy buồn. Nhưng Nhung hoàn toàn tôn trọng quyết định của con về việc chọn ngành nghề và tương lai của mình. Ba mẹ sẽ đứng sau và là người đưa cho con những lời khuyên và chỉ có thể đồng hành cùng con tới một mốc thời gian nào đó. Về sau, con phải đi làm và tự có trách nhiệm với cuộc đời của mình. - Có con gái đang ở tuổi lớn lại xa bố mẹ và tiếp xúc một nền văn hóa phương Tây cởi mở, Đinh Y Nhung đã khuyên dạy và đồng hành với con như thế nào? Ngay khi ở Việt Nam, con gái Nhung đã được theo học trường quốc tế. Hai mẹ con cũng có rất nhiều dịp để tâm sự và chia sẻ với nhau. Ngay từ nhỏ, Nhung đã cho bé được tiếp xúc song song giữa hai nền văn hóa để con không bỡ ngỡ. Mình là người Việt nên đương nhiên vẫn dạy con theo văn hóa Á Đông là chủ yếu. Nhung vẫn luôn tạo điều kiện để con cảm nhận những nét đẹp trong nền văn hóa quê hương. Văn hóa phương Tây thì xa lạ hơn nhưng Nhung cũng khuyên con rằng điều gì hay thì mình học hỏi, cái gì không tốt thì mình nên bỏ qua. Tất nhiên mình không thể theo sát con, nhất là khi bé đang ở độ tuổi mới lớn, có nhiều sự hiếu kỳ. Tuy nhiên, Nhung cũng không quá lo lắng vì qua quá trình học tập ở các trường quốc tế, bé cùng đã được làm quen dần với văn hóa phương Tây. Bé muốn làm bạn với mẹ nên có nhiều thứ bé muốn hỏi, muốn tiếp thu thì hai mẹ con lại ngồi xuống chia sẻ, tâm sự với nhau. Nhung tin, con luôn tỉnh táo để đưa ra những quyết định cho bản thân mình. Nhung không dám nói trước, nhưng hiện tại con vẫn luôn biết nói cảm ơn, xin phép trước khi làm bất cứ điều gì nên mình vẫn rất tin tưởng con. - Chị nhận xét thế nào về tính cách của con gái? Phải chăng bé là phiên bản nhí của chị? Con gái Nhung có nhiều nét giống mẹ. - Ngữ cảnh 5: . - Trong quá trình quay phim, má Hiền có tham gia đóng góp ý kiến cho dàn diễn viên trẻ không? Không phải má Hiền muốn làm thầy nhưng có những lúc cũng lên tiếng góp ý một vài điều. Những lúc như thế các bạn diễn viên trẻ cũng nghe theo. Phải giúp đỡ nhau như vậy mới có thể tạo ra được một tác phẩm hay. Chứ có nhiều diễn viên trẻ có lòng tự trọng cao, chỉ khi đạo diễn nói mới nghe thì không bao giờ có thể tiến bộ được. Má Hiền phải cảm thấy hạnh phúc mới đúng, càng ngày xung quanh càng có nhiều bạn bè, các mối quan hệ nhờ đó mà cũng ngày càng đông. Ngày xưa, khi tham gia là Mùi Ngò Gai chưa có ai biết nhưng sau khi phim phát sóng mọi người đã nhớ đến má. Hiện tại, má Hiền đã được đạo diễn, nhà sản xuất mời đóng phim đó đã là một niềm hạnh phúc. Đi ra đường hay đi khám bệnh, người ta cứ vây xung quanh quan tâm hỏi han khiến má cảm thấy rất vui lắm (cười). Cảm ơn nghệ sĩ Thanh Hiền đã nhận lời tham gia phỏng vấn với SAOstar. Chúc má có nhiều sức khỏe để tiếp tục làm nghề!''' question = '''Tại sao các thân vương triều Thanh không dám tạo phản mặc dù có nhiều quyền lực và cơ hội?''' '''Trả lời: Các thân vương triều Thanh không dám tạo phản mặc dù có nhiều quyền lực và cơ hội vì có ba lý do chính: 1. **Không thể nối ngôi**: Để duy trì danh phận thân vương, họ phải có sự đồng ý của hoàng đế và phải lập được công lao cho đất nước. Điều này hạn chế cơ hội của họ để trở thành hoàng đế. 2. **Giám sát nghiêm ngặt**: Triều đình tiến hành giám sát nghiêm ngặt đối với các thân vương, không cho họ cơ hội để tạo phản. 3. **Bị cô lập**: Các thân vương không thể giao thiệp quá sâu với các đại thần, quan lại khác, điều này khiến họ bị cô lập và không có cơ hội cấu kết với người khác để tạo phản.''' ``` #### 3. Loại bỏ negative ```python context = '''- Ngữ cảnh 1: Thái Bình hướng đến là trung tâm công nghiệp, năng lượng của vùng Với tiềm năng sẵn có, quy hoạch tỉnh Thái Bình thời kỳ 2021-2030, tầm nhìn đến năm 2050 xác định tỉnh sẽ phát triển công nghiệp theo hướng hiện đại, bền vững dựa trên nghiên cứu phát triển điện gió, điện khí, cân bằng lượng phát thải. Sáng 5/3, UBND tỉnh Thái Bình tổ chức Hội nghị công bố quy hoạch của tỉnh thời kỳ 2021-2030, tầm nhìn đến năm 2050 và xúc tiến đầu tư tỉnh Thái Bình. Phát biểu tại hội nghị, Phó Chủ tịch Thường trực UBND tỉnh Nguyễn Quang Hưng cho biết: Mục tiêu của quy hoạch là đến năm 2030, Thái Bình trở thành địa phương thuộc nhóm phát triển khá và là một trong những trung tâm phát triển công nghiệp của vùng Đồng bằng sông Hồng, có cơ cấu kinh tế hiện đại với công nghiệp là động lực chủ yếu cho tăng trưởng để Thái Bình phát triển nhanh, toàn diện và bền vững. Đến năm 2050, Thái Bình là tỉnh phát triển của vùng Đồng bằng sông Hồng, tăng trưởng kinh tế dựa trên nền tảng khoa học công nghệ, đổi mới sáng tạo và các ngành kinh tế trụ cột có sức cạnh tranh cao. Quy hoạch tỉnh đã xác định 4 trụ cột tăng trưởng, 3 khâu đột phá, 4 không gian kinh tế - xã hội, 3 hành lang kinh tế, định hướng phát triển các ngành và lĩnh vực và 6 nhiệm vụ trọng tâm. Quy hoạch tỉnh cũng có nhiều điểm mới, đột phá như mở ra không gian phát triển mới thông qua hoạt động “lấn biển”, tạo quỹ đất cho các hoạt động chức năng, hình thành không gian công nghiệp - đô thị - dịch vụ. Về hạ tầng giao thông, Thái Bình sẽ đầu tư 3 tuyến cao tốc là cao tốc Ninh Bình - Hải Phòng (CT.08), đường vành đai 5 - Hà Nội (CT.39) và tuyến CT.16 kết nối Khu kinh tế với thành phố Thái Bình và vùng kinh tế phía Tây Bắc Thủ đô. Tỉnh cũng sẽ đầu tư 101km đường sắt, khổ đường dự kiến rộng 1.435 mm và sân bay chuyên dụng nằm ở ven biển Thái Bình. Về phát triển kinh tế, quy hoạch tỉnh Thái Bình xác định tỉnh sẽ phát triển công nghiệp theo hướng hiện đại, công nghệ tiên tiến, giá trị gia tăng cao, tham gia sâu, toàn diện vào mạng lưới sản xuất, chuỗi giá trị toàn cầu, phát huy các tiềm năng, thế mạnh để đưa Thái Bình trở thành một trong những trung tâm phát triển công nghiệp, năng lượng của vùng Đồng bằng sông Hồng. Tỉnh khuyến khích đầu tư phát triển các ngành có thế mạnh và có thể tạo đột phá như năng lượng, cơ khí chế biến, chế tạo, công nghiệp công nghệ cao, điện - điện tử, chế biến sản phẩm nông, lâm nghiệp và thủy sản… Đồng thời, tập trung nghiên cứu phát triển điện gió, điện khí để tạo nguồn điện sạch và cân bằng lượng phát thải, nghiên cứu đầu tư xây dựng nhà máy chế biến Condensate, chuẩn bị mọi điều kiện để xây dựng và đưa vào vận hành Nhà máy nhiệt điện LNG Thái Bình. Về nông nghiệp, tỉnh Thái Bình vẫn xác định đây là \"trụ cột quan trọng\" trong phát triển kinh tế của tỉnh, góp phần bảo đảm an ninh lương thực quốc gia, hướng tới trở thành trung tâm sản xuất nông nghiệp hàng đầu của Đồng bằng sông Hồng. Phát biểu tại hội nghị, Phó Thủ tướng Chính phủ Trần Lưu Quang đánh giá Thái Bình có 4 tiềm năng, lợi thế lớn để có thể có sự bứt phá trong thời gian tới như vị trí địa lý và tiếp cận đất đai thuận lợi; từng là địa phương đi đầu trong xây dựng nông thôn mới bài bản và nghiêm túc, nhận được sự quan tâm của nhiều thế hệ lãnh đạo Đảng, Nhà nước và có nhiều doanh nhân người Thái Bình và luôn hướng về quê hương; có sự đoàn kết, thống nhất, trước hết là trong tập thể lãnh đạo. Về vị trí địa lý và tiếp cận đất đai, Phó Thủ tướng cho rằng trong tương lai, khi Luật Đất đai có hiệu lực, Thái Bình sẽ có nhiều điều kiện lấn biển để triển khai các dự án khu đô thị, khu công nghiệp thân thiện với môi trường. Đối với nông nghiệp, Phó Thủ tướng nhấn mạnh về lâu dài Thái Bình có thể ghi điểm từ phát triển công nghiệp nhưng trước mắt, đặc biệt trong lúc khó khăn thì nông nghiệp vẫn là nền tảng rất quý giá. Mặt khác, ứng dụng của công nghệ cao trong sản xuất nông nghiệp sẽ rút ngắn thời gian làm đồng của người nông dân, tạo điều kiện để Thái Bình huy động nguồn nhân lực trong nông nghiệp sang phát triển các ngành công nghiệp và dịch vụ, một lợi thế mà không phải địa phương nào cũng có được như Thái Bình. Bên cạnh những lợi thế trên, lãnh đạo Chính phủ chỉ ra một số khó khăn mà tỉnh phải đối mặt như Thái Bình đã sử dụng hết 1.600 ha chỉ tiêu đất công nghiệp trong giai đoạn này, đòi hỏi phải có phương án giải quyết thấu đáo trong thời gian tới để tỉnh tiếp tục phát triển công nghiệp. Đồng thời, Thái Bình cũng phải cạnh tranh với những địa phương như Hải Phòng, Quảng Ninh trong thu hút FDI trong khi phát triển cơ sở hạ tầng chưa theo kịp mong muốn. Do vậy, khi triển khai quy hoạch tỉnh, Phó Thủ tướng nhắn nhủ tới địa phương 8 chữ: Tuân thủ, linh hoạt, đồng bộ và thấu hiểu. Đồng thời, tỉnh cũng phải \"linh hoạt\" trong tổ chức thực hiện, trong trường hợp cá biệt cụ thể, điều chỉnh mục tiêu cho phù hợp. Sáng cùng ngày, Phó Thủ tướng Trần Lưu Quang đã dự Lễ khởi công dự án Nhà máy Pegavision Việt Nam tại khu công nghiệp Liên Hà Thái, huyện Thái Thụy, tỉnh Thái Bình - Ngữ cảnh 2: Bình Định được định hướng là trung tâm khoa học, công nghệ đổi mới sáng tạo Tỉnh Bình Định được định hướng phát triển ngành công nghiệp phát triển theo hướng hiện đại, quy mô lớn, trở thành một trong những trung tâm công nghiệp chế biến chế tạo và công nghệ cao của vùng Bắc Trung Bộ và duyên hải Trung Bộ. Theo Quy hoạch tỉnh Bình Định thời kỳ 2021 - 2030, tầm nhìn đến năm 2050 vừa được Thủ tướng Chính phủ phê duyệt, tỉnh Bình Định được định hướng phát triển ngành công nghiệp phát triển theo hướng hiện đại, quy mô lớn, trở thành một trong những trung tâm công nghiệp chế biến chế tạo và công nghệ cao của vùng Bắc Trung Bộ và duyên hải Trung Bộ. Ngành công nghiệp tăng trưởng nhanh, bền vững, hướng tới tăng trưởng xanh, kinh tế tuần hoàn là trụ cột để phát triển và chuyển dịch cơ cấu kinh tế của tỉnh. Ngành chế biến, chế tạo công nghệ cao (dịch chuyển ngành công nghiệp chế biến, chế tạo sang lĩnh vực sản xuất có giá trị gia tăng cao như: chế biến sâu nông - thủy - hải sản, linh kiện điện tử, bán dẫn, dược phẩm), công nghệ thông tin, trí tuệ nhân tạo trở thành một trong những lĩnh vực đột phá, góp phần đưa tỉnh Bình Định trở thành một trung tâm khoa học, công nghệ đổi mới sáng tạo của vùng và cả nước. Quy hoạch tỉnh Bình Định thời kỳ 2021 - 2030, tầm nhìn đến năm 2050 đặt ra yêu cầu tỉnh này phải chú trọng thu hút đầu tư phát triển năng lượng tái tạo, năng lượng sạch như điện gió ven bờ, điện gió ngoài khơi, điện mặt trời, điện sinh khối và nguồn năng lượng mới (hydrogen/amoniac xanh…); các dự án sản xuất thép quy mô lớn, đóng tàu, sản xuất thiết bị phụ trợ điện gió có công nghệ tiên tiến để nâng cấp xây dựng hạ tầng kỹ thuật sản xuất, thúc đẩy chuyển dịch kinh tế. Quy hoạch tỉnh Bình Định thời kỳ 2021 - 2030, tầm nhìn đến năm 2050 cũng đặt ra mục tiêu đến năm 2030, Bình Định trở thành tỉnh phát triển thuộc nhóm dẫn đầu vùng Bắc Trung Bộ và duyên hải Trung Bộ, là trung tâm công nghiệp chế biến, chế tạo, dịch vụ, du lịch và văn hóa phía Nam của vùng; trung tâm lớn của cả nước về phát triển kinh tế biển; trọng điểm du lịch quốc gia và quốc tế với hệ thống kết cấu hạ tầng kinh tế đồng bộ, hiện đại; kinh tế của tỉnh phát triển nhanh, bền vững và xanh dựa trên các trụ cột tăng trưởng công nghiệp, dịch vụ du lịch, cảng biển - logistics; nông nghiệp ứng dụng công nghệ cao; đô thị hóa; thực hiện thành công các mục tiêu chuyển đổi số, đổi mới sáng tạo, cải thiện mạnh mẽ môi trường đầu tư kinh doanh, trở thành điểm đến đầu tư hấp dẫn của các doanh nghiệp lớn trong và ngoài nước; chỉ số năng lực cạnh tranh cấp tỉnh thuộc nhóm cao của cả nước; kết cấu hạ tầng kinh tế - xã hội đồng bộ, hiện đại, hệ thống đô thị phát triển theo hướng đô thị thông minh, kết nối thuận tiện với các trung tâm kinh tế của vùng, cả nước và quốc tế. - Ngữ cảnh 3: . Chủ tịch UBND tỉnh Quảng Ninh cho biết, tỉnh đặt mục tiêu hướng đến năm 2030 trở thành một tỉnh tiêu biểu của cả nước về mọi mặt; tỉnh kiểu mẫu giàu đẹp, văn minh, hiện đại, nâng cao đời sống mọi mặt của nhân dân; cực tăng trưởng của khu vực phía Bắc, một trong những trung tâm phát triển năng động, toàn diện; trung tâm du lịch quốc tế, trung tâm kinh tế biển, cửa ngõ của Vùng kinh tế trọng điểm Bắc Bộ và cả nước. Để đạt được những mục tiêu trên, tỉnh Quảng Ninh xác định sự đóng góp, quan tâm của cộng đồng doanh nghiệp, nhất là các doanh nghiệp hàng đầu Việt Nam “các sếu đầu đàn” là một trong những yếu tố then chốt quyết định. Do vậy, tỉnh Quảng Ninh rất mong nhận được sự quan tâm, nghiên cứu đầu tư hợp tác của các Doanh nghiệp hàng đầu Việt Nam trong thời gian tới, nhất là trong việc đầu tư các dự án có hàm lượng công nghệ cao, công nghệ tiên tiến, quản trị hiện đại, giá trị gia tăng cao, có tác động lan tỏa. Tỉnh Quảng Ninh cam kết tạo điều kiện thuận lợi nhất cho doanh nghiệp phát triển hơn nữa khi đầu tư kinh doanh trên địa bàn tỉnh; cam kết đồng hành, lắng nghe tiếng nói của cộng đồng doanh nghiệp, các nhà đầu tư; cùng trăn trở, trách nhiệm, giải quyết thấu đáo, vào cuộc thực chất, hiệu quả đối với từng khó khăn, vướng mắc với mục tiêu tăng cường niềm tin và nâng cao sự hài lòng của cá nhân, tổ chức, doanh nghiệp là thước đo đánh giá chất lượng phục vụ, chất lượng điều hành của cơ quan hành chính nhà nước từ cấp tỉnh đến các cấp cơ sở. Tỉnh Quảng Ninh sẽ triển khai một cách hiệu quả nhất Quy hoạch tỉnh, quy hoạch các địa phương; chuẩn bị mặt bằng sạch; quỹ đất tái định cư; đảm bảo nguồn cung điện, nước và viễn thông theo yêu cầu; xây dựng các chính sách đột phá để thu hút nguồn nhân lực chất lượng cao thông qua việc cải thiện nhà ở và cơ sở văn hóa để đảm bảo đời sống vật chất và tinh thần cho người lao động. Đồng thời bảo vệ quyền và lợi ích chính đáng, hợp pháp của nhà đầu tư, doanh nghiệp vào tỉnh; bảo đảm hài hòa lợi ích giữa nhà nước, nhà đầu tư, người lao động và người dân.''' question = '''Theo quy hoạch tỉnh Tây Ninh thời kỳ 2021 - 2030, tầm nhìn đến năm 2050, tỉnh sẽ tập trung phát triển công nghiệp và dịch vụ du lịch. Trong bối cảnh cạnh tranh với các tỉnh lân cận, yếu tố nào được coi là quan trọng nhất để Tây Ninh có thể thu hút đầu tư và phát triển nhanh, toàn diện và bền vững?''' '''Trả lời: Trong ngữ cảnh được cung cấp, không có thông tin về quy hoạch tỉnh Tây Ninh thời kỳ 2021 - 2030, tầm nhìn đến năm 2050. Do đó, không có câu trả lời chính xác dựa trên các thông tin đã cung cấp. Nếu bạn có thêm thông tin về quy hoạch tỉnh Tây Ninh, vui lòng cung cấp để tôi có thể trả lời câu hỏi một cách chính xác và đầy đủ. ''' ``` #### 4. Tích hợp thông tin ```python context = '''- Ngữ cảnh 1: 43/2020/nđ-cp Điều 3. Chế độ, chính sách đối với người tham gia thi hành án tử hình\n1. Người tham gia Đội thi hành án tử hình được hưởng chế độ bồi dưỡng bằng ba lần mức lương cơ sở khi thi hành án tử hình đối với 01 người và nghỉ dưỡng 10 ngày theo quy định chung về chế độ nghỉ dưỡng đối với cán bộ, chiến sĩ Công an nhân dân, Quân đội nhân dân.\n2. Người tham gia Hội đồng thi hành án tử hình, cán bộ quản giáo, người ghi âm, ghi hình, chụp ảnh, phiên dịch, thực hiện lăn tay người bị thi hành án tử hình, khâm liệm, mai táng tử thi được hưởng chế độ bồi dưỡng bằng một lần mức lương cơ sở khi thi hành án tử hình đối với 01 người.\n3. Người tham gia bảo đảm an ninh, trật tự; đại diện Ủy ban nhân dân cấp xã; Điều tra viên được hưởng chế độ bồi dưỡng bằng một phần hai mức lương cơ sở khi thi hành án tử hình đối với 01 người. - Ngữ cảnh 2: 53/2010/qh12 Điều 60. Giải quyết việc xin nhận tử thi, hài cốt của người bị thi hành án tử hình\n1. Việc giải quyết nhận tử thi được thực hiện như sau:\na) Trước khi thi hành án tử hình, thân nhân hoặc người đại diện hợp pháp của người chấp hành án được làm đơn có xác nhận của Ủy ban nhân dân cấp xã nơi cư trú gửi Chánh án Tòa án đã xét xử sơ thẩm đề nghị giải quyết cho nhận tử thi của người chấp hành án để an táng; trường hợp người chấp hành án là người nước ngoài thì đơn phải có xác nhận của cơ quan có thẩm quyền hoặc cơ quan đại diện ngoại giao tại Việt Nam của nước mà người chấp hành án mang quốc tịch và phải được dịch ra tiếng Việt. Đơn phải ghi rõ họ tên, địa chỉ người nhận tử thi, quan hệ với người chấp hành án; cam kết bảo đảm yêu cầu về an ninh, trật tự, vệ sinh môi trường và tự chịu chi phí;\nb) Chánh án Tòa án đã xét xử sơ thẩm thông báo bằng văn bản cho người có đơn đề nghị về việc cho nhận tử thi hoặc không cho nhận tử thi khi có căn cứ cho rằng việc nhận tử thi ảnh hưởng đến an ninh, trật tự, vệ sinh môi trường. Trường hợp người chấp hành án là người nước ngoài, thì Chánh án Tòa án đã xét xử sơ thẩm có trách nhiệm thông báo bằng văn bản cho Bộ Ngoại giao Việt Nam để thông báo cho cơ quan có thẩm quyền hoặc cơ quan đại diện ngoại giao tại Việt Nam của nước mà người đó mang quốc tịch;\nc) Cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu có trách nhiệm thông báo cho người có đơn đề nghị ngay sau khi thi hành án để đến nhận tử thi về an táng. Việc giao nhận tử thi phải được thực hiện trong thời hạn 24 giờ kể từ khi thông báo và phải lập biên bản, có chữ ký của các bên giao, nhận; hết thời hạn này mà người có đơn đề nghị không đến nhận tử thi thì cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu có trách nhiệm an táng.\n2. Trường hợp không được nhận tử thi hoặc thân nhân của người bị thi hành án không có đơn đề nghị được nhận tử thi về an táng thì cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu tổ chức việc an táng. Sau 03 năm kể từ ngày thi hành án, thân nhân hoặc đại diện hợp pháp của người đã bị thi hành án được làm đơn có xác nhận của Ủy ban nhân dân cấp xã nơi cư trú đề nghị Cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu nơi đã thi hành án cho nhận hài cốt. Đơn đề nghị phải ghi rõ họ tên, địa chỉ người nhận hài cốt, quan hệ với người bị thi hành án; cam kết bảo đảm yêu cầu về an ninh, trật tự, vệ sinh môi trường và tự chịu chi phí. Trong thời hạn 07 ngày, kể từ ngày nhận được đơn, cơ quan thi hành án hình sự Công an cấp tỉnh, cơ quan thi hành án hình sự cấp quân khu có trách nhiệm xem xét, giải quyết.\nTrường hợp người bị thi hành án là người nước ngoài thì đơn đề nghị phải có xác nhận của cơ quan có thẩm quyền hoặc cơ quan đại diện ngoại giao tại Việt Nam của nước mà người bị thi hành án mang quốc tịch và phải được dịch ra tiếng Việt. Việc giải quyết cho nhận hài cốt do cơ quan quản lý thi hành án hình sự xem xét, quyết định. - Ngữ cảnh 3: 53/2010/qh12 Điều 57. Chế độ quản lý giam giữ, ăn, ở, mặc, sinh hoạt, gửi và nhận thư, nhận đồ vật, tiền mặt, gặp thân nhân, chăm sóc y tế\nChế độ quản lý giam giữ, ăn, ở, mặc, sinh hoạt, gửi và nhận thư, nhận đồ vật, tiền mặt, gặp thân nhân, chăm sóc y tế đối với người bị kết án tử hình trong thời gian chờ thi hành án thực hiện theo quy định của pháp luật về tạm giam. - Ngữ cảnh 4: 82/2011/nđ-cp Điều 9. Chi phí mai táng\nChi phí mai táng người bị thi hành án tử hình bao gồm: 01 quan tài bằng gỗ thường, 01 bộ quần áo thường, 04 m vải liệm, hương, nến, rượu, cồn để làm vệ sinh khi liệm tử thi và các chi phí mai táng khác.\nTrường hợp thân nhân hoặc người đại diện hợp pháp của người bị kết án tử hình được nhận tử thi về mai táng thì phải tự chịu chi phí đưa di chuyển tử thi và phải cam kết chấp hành đúng quy định của pháp luật về bảo đảm an ninh, trật tự. - Ngữ cảnh 5: 82/2011/nđ-cp Điều 5. Chế độ, chính sách đối với người tham gia thi hành án tử hình\n1. Người tham gia Đội thi hành án tử hình và bác sĩ xác định tĩnh mạch được hưởng chế độ bồi dưỡng bằng hai lần mức lương tối thiểu chung cho mỗi lần thi hành án và được nghỉ dưỡng 10 ngày theo quy định chung về chế độ nghỉ dưỡng đối với cán bộ, chiến sĩ Công an nhân dân, Quân đội nhân dân.\n2. Người tham gia Hội đồng thi hành án tử hình, bác sĩ pháp y, cán bộ chuyên môn, người thực hiện lăn tay người bị thi hành án tử hình, khâm liệm, an táng tử thi được hưởng chế độ bồi dưỡng bằng một lần mức lương tối thiểu chung quy định cho mỗi lần thi hành án.\n3. Những người tham gia khác được hưởng chế độ bồi dưỡng bằng một phần hai mức lương tối thiểu cho mỗi lần thi hành án.''' question = '''Tử tù chết sau khi tiêm thuốc độc mà không có thân nhân nhận xác thì được hỗ trợ mai táng như thế nào?''' '''Trả lời: Dựa trên ngữ cảnh 2 (53/2010/qh12 Điều 60), nếu tử tù chết sau khi tiêm thuốc độc mà không có thân nhân nhận xác, thì cơ quan thi hành án hình sự Công an cấp tỉnh hoặc cơ quan thi hành án hình sự cấp quân khu sẽ tổ chức việc an táng. Cụ thể: 1. **An táng**: Cơ quan thi hành án hình sự Công an cấp tỉnh hoặc cơ quan thi hành án hình sự cấp quân khu sẽ chịu trách nhiệm an táng tử tù nếu không có thân nhân hoặc người đại diện hợp pháp đề nghị nhận tử thi. 2. **Hài cốt sau 3 năm**: Sau 3 năm kể từ ngày thi hành án, nếu thân nhân hoặc đại diện hợp pháp của người đã bị thi hành án vẫn chưa đề nghị nhận hài cốt, họ có thể làm đơn đề nghị Cơ quan thi hành án hình sự Công an cấp tỉnh hoặc cơ quan thi hành án hình sự cấp quân khu nơi đã thi hành án cho nhận hài cốt. Đơn đề nghị phải ghi rõ họ tên, địa chỉ người nhận hài cốt, quan hệ với người bị thi hành án, cam kết bảo đảm yêu cầu về an ninh, trật tự, vệ sinh môi trường và tự chịu chi phí. 3. **Chi phí mai táng**: Theo ngữ cảnh 4 (82/2011/nđ-cp Điều 9), chi phí mai táng bao gồm: - 01 quan tài bằng gỗ thường. - 01 bộ quần áo thường. - 04 m vải liệm. - Hương, nến, rượu, cồn để làm vệ sinh khi liệm tử thi. - Các chi phí mai táng khác. Nếu thân nhân hoặc người đại diện hợp pháp đề nghị nhận tử thi về mai táng, họ phải tự chịu chi phí đưa di chuyển tử thi và cam kết chấp hành đúng quy định của pháp luật về bảo đảm an ninh, trật tự. ''' ``` - Ngữ cảnh 2 và ngữ cảnh 4 có chứa phần thông tin cho việc trả lời câu hỏi. ### 5.Xác định positive/negative ```python system_prompt = "Bạn là một trợ lí Tiếng Việt nhiệt tình và trung thực. Hãy luôn trả lời một cách hữu ích nhất có thể." template = '''Hãy xác định xem ngữ cảnh có chứa đầy đủ thông tin để trả lời câu hỏi hay không. Chỉ cần đưa ra 1 trong 2 đáp án trong phần trả lời là "Có" hoặc "Không". ### Ngữ cảnh : {context} ### Câu hỏi : {question} ### Trả lời :''' context = '''Công dụng thuốc Xelocapec Capecitabine là một hoạt chất gây độc chọn lọc với tế bào ung thư. Hoạt chất này có trong thuốc Xelocapec. Vậy thuốc Xelocapec có tác dụng gì và cần lưu ý những vấn đề nào khi điều trị bằng sản phẩm này? 1. Xelocapec là thuốc gì? Xelocapec chứa hoạt chất Capecitabine hàm lượng 500mg. Thuốc Xelocapec bào chế dạng viên nén bao phim và đóng gói mỗi hộp 3 vỉ x 10 viên. Xelocapec chứa hoạt chất Capecitabine là một dẫn chất Fluoropyrimidine carbamate với tác dụng gây độc chọn lọc với các tế bào ung thư . Mặc dù trên in vitro Capecitabine không cho thấy tác dụng độc tế bào nhưng trên in vivo, Xelocapec biến đổi liên tiếp thành chất gây độc tế bào là 5-fluorouracil (5-FU). Sự hình thành 5-FU tại khối u thông qua xúc tác một cách tối ưu của yếu tố tạo mạch liên quan là Thymidine phosphorylase, qua đó hạn chế tối đa mức độ ảnh hưởng đến nhu mô lành của 5-FU. 2. Thuốc Xelocapec có tác dụng gì? Thuốc Xelocapec được chỉ định điều trị đơn lẻ hoặc kết hợp với các liệu pháp điều trị ung thư. Xelocapec làm chậm hoặc ngăn chặn sự tăng trưởng của tế bào ung thư, do đó giảm kích thước khối u trong những trường hợp sau: Ung thư vú : Xelocapec phối hợp với Docetaxel được chỉ định điều trị ung thư vú thể tiến triển tại chỗ hoặc di căn sau khi đã thất bại với liệu pháp hóa trị; Ung thư đại trực tràng : Xelocapec được chỉ định hỗ trợ điều trị ung thư đại tràng sau phẫu thuật hoặc ung thư đại trực tràng di căn; Ung thư dạ dày : Xelocapec phối hợp với hợp chất platin được chỉ định điều trị khởi đầu cho những bệnh nhân ung thư dạ dày. Chống chỉ định của thuốc Xelocapec : Bệnh nhân quá mẫn cảm với Capecitabine hay các thành phần khác có trong Xelocapec ; Người có tiền sử gặp các phản ứng không mong muốn nghiêm trọng khi điều trị với Fluoropyrimidine; Người đang mang thai hoặc cho con bú; Suy thận nặng (độ thanh thải Creatinin <30mL/phút); Bệnh nhân đang điều trị ung thư với Sorivudin hoặc chất tương tự về mặt hóa học như Brivudin; Bệnh nhân thiếu hụt Dihydropyrimidin dehydrogenase; Bệnh nhân giảm số lượng bạch cầu hoặc tiểu cầu nặng; Suy gan nặng. 3. Liều dùng của thuốc Xelocapec Liều dùng của Xelocapec khi điều trị đơn lẻ: Ung thư đại trực tràng, ung thư vú: 1250mg/m2, uống 2 lần mỗi ngày trong thời gian 14 ngày, tiếp sau đó là 7 ngày ngưng thuốc. Liều Xelocapec trong điều trị phối hợp: Ung thư vú: Liều khởi đầu là 1250mg/m2, 2 lần uống mỗi ngày trong 2 tuần dùng phối hợp với Docetaxel, tiếp sau đó lá 1 tuần ngưng thuốc; Ung thư dạ dày, đại trực tràng: Liều khuyến cáo là 800-1000mg/m2/lần x 2 lần/ngày trong thời gian 2 tuần, sau đó 7 ngày ngưng thuốc hoặc 625mg/m2/lần x 2 lần mỗi ngày khi điều trị liên tục. Thuốc Xelocapec nên uống cùng với thức ăn, do đó thời điểm tốt nhất là trong vòng 30 phút sau bữa ăn. 4. Tác dụng phụ của thuốc Xelocapec Các triệu chứng bất thường như buồn nôn, nôn ói, giảm cảm giác ngon miệng, táo bón, cơ thể mệt mỏi, yếu sức, đau đầu, chóng mặt, khó ngủ có thể xảy ra trong thời gian dùng Xelocapec . Trong đó, tình trạng buồn nôn và nôn ói có thể nghiêm trọng nên đôi khi cần được bác sĩ chỉ định thuốc kiểm soát phù hợp. Tiêu chảy là một tác dụng phụ phổ biến khác của thuốc Xelocapec . Bệnh nhân cần uống nhiều nước khi điều trị bằng Xelocapec trừ khi bác sĩ có hướng dẫn khác. Nôn ói hoặc tiêu chảy kéo dài do thuốc Xelocapec có thể dẫn đến mất nước nghiêm trọng, vì vậy người bệnh hãy liên hệ ngay với bác sĩ nếu có các triệu chứng mất nước như giảm đi tiểu, khô miệng, tăng cảm giác khát nước hoặc chóng mặt. Tình trạng rụng tóc tạm thời xảy ra trong thời gian dùng thuốc Xelocapec và có thể hồi phục sau khi điều trị đã kết thúc. Một số bệnh nhân ghi nhận hiện tượng thay đổi móng tay tạm thời. Đối với nam giới và phụ nữ trong độ tuổi sinh đẻ, thuốc Xelocapec có thể ảnh hưởng đến khả năng có con của bệnh nhân. Bệnh nhân hãy tham khảo ý kiến bác sĩ để biết thêm chi tiết. Thuốc Xelocapec có thể làm giảm khả năng miễn dịch của cơ thể với các tác nhân nhiễm trùng, dẫn đến tăng nguy cơ mắc các bệnh nhiễm trùng nghiêm trọng (nhưng hiếm khi gây tử vong) hoặc làm cho bệnh nhiễm trùng hiện mắc nghiêm trọng hơn. Phản ứng dị ứng rất nghiêm trọng với thuốc Xelocapec rất hiếm khi xảy ra. Tuy nhiên, bệnh nhân hãy liên hệ với bác sĩ ngay lập tức nếu xuất hiện các triệu chứng của phản ứng dị ứng nghiêm trọng như phát ban, sưng ngứa mặt/lưỡi/họng, chóng mặt nghiêm trọng hoặc khó thở. 5. Tương tác thuốc của Xelocapec Hoạt chất Capecitabine trong thuốc Xelocapec có thể xảy ra tương tác thuốc nghiêm trọng với một số thuốc sau: Thuốc chống đông máu Coumarin: Trong một nghiên cứu tương tác lâm sàng, sau khi dùng Warfarin liều đơn 20mg kết hợp với Capecitabine làm tăng AUC của S-warfarin khoảng 57% và giá trị INR tăng 91%.''' question = '''Tại sao Capecitabine trong Xelocapec không gây độc tế bào trên in vitro nhưng lại biến đổi thành 5-fluorouracil (5-FU) gây độc tế bào trên in vivo, và cơ chế nào giúp hạn chế ảnh hưởng đến nhu mô lành của 5-FU?''' '''Trả lời: Có''' ``` **Next release** Mô hình phiên bản tiếp theo mạnh mẽ hơn, giải quyết các dữ liệu phức tạp hơn sẽ được public sớm nhất có thể. **Developer** Member: Nguyễn Nho Trung, Nguyễn Nhật Quang ## Contact **Email**: nguyennhotrung3004@gmail.com ## Citation ```Plaintext @misc{ViRAG-Gen, title={ViRAG-Gen: Towards a specialized LLM for RAG task in Vietnamese language.}}, author={Nguyen Nho Trung, Nguyen Nhat Quang}, year={2024}, publisher={Huggingface}, } ```
helmutsukocok/blockassist-bc-loud_scavenging_kangaroo_1755788112
helmutsukocok
2025-08-21T15:21:40Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "loud scavenging kangaroo", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:21:37Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - loud scavenging kangaroo --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
thanobidex/blockassist-bc-colorful_shiny_hare_1755788077
thanobidex
2025-08-21T15:21:39Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "colorful shiny hare", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:21:36Z
--- 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).
mytestorg007/fu51fp16
mytestorg007
2025-08-21T15:20:57Z
0
0
null
[ "license:apache-2.0", "region:us" ]
null
2025-08-21T15:20:57Z
--- license: apache-2.0 ---
Dejiat/blockassist-bc-savage_unseen_bobcat_1755789591
Dejiat
2025-08-21T15:20:56Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "savage unseen bobcat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:20:50Z
--- 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).
ganga4364/mms_300_Garchen_Rinpoche-v6-ft-Checkpoint-26000
ganga4364
2025-08-21T15:20:43Z
0
0
transformers
[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2025-08-21T15:18:07Z
--- 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]
Medved444/blockassist-bc-bellowing_finicky_manatee_1755788337
Medved444
2025-08-21T15:20:09Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "bellowing finicky manatee", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:19:35Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - bellowing finicky manatee --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
jaimefrevoltio/smolvla_t1_fold_v1_biarm_s101
jaimefrevoltio
2025-08-21T15:19:49Z
0
0
lerobot
[ "lerobot", "safetensors", "robotics", "smolvla", "dataset:jaimefrevoltio/fold_v1_biarm_s101", "arxiv:2506.01844", "base_model:lerobot/smolvla_base", "base_model:finetune:lerobot/smolvla_base", "license:apache-2.0", "region:us" ]
robotics
2025-08-21T15:19:38Z
--- base_model: lerobot/smolvla_base datasets: jaimefrevoltio/fold_v1_biarm_s101 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
lautan/blockassist-bc-gentle_patterned_goat_1755787891
lautan
2025-08-21T15:18:54Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "gentle patterned goat", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:18:50Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - gentle patterned goat --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
phospho-app/myzxyz-gr00t-my_dataset-7zakn
phospho-app
2025-08-21T15:18:40Z
0
0
phosphobot
[ "phosphobot", "safetensors", "gr00t_n1_5", "gr00t", "robotics", "dataset:myzxyz/my_dataset", "region:us" ]
robotics
2025-08-21T14:53:11Z
--- datasets: myzxyz/my_dataset library_name: phosphobot pipeline_tag: robotics model_name: gr00t tags: - phosphobot - gr00t task_categories: - robotics --- # gr00t Model - phospho Training Pipeline ## This model was trained using **phospho**. Training was successful, try it out on your robot! ## Training parameters: - **Dataset**: [myzxyz/my_dataset](https://huggingface.co/datasets/myzxyz/my_dataset) - **Wandb run URL**: None - **Epochs**: 10 - **Batch size**: 107 - **Training steps**: None 📖 **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme) 🤖 **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
popcion/panel_detection
popcion
2025-08-21T15:17:19Z
0
0
null
[ "license:apache-2.0", "region:us" ]
null
2025-08-11T19:12:09Z
--- license: apache-2.0 ---
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755787611
katanyasekolah
2025-08-21T15:17:10Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "silky sprightly cassowary", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:17:06Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - silky sprightly cassowary --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
Jr12lm12/mistral-7b-instruct-v0.3-bnb-De_En_Solar-QLORA
Jr12lm12
2025-08-21T15:17:00Z
0
0
transformers
[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]
null
2025-08-21T15:15:38Z
--- base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - **Developed by:** Jr12lm12 - **License:** apache-2.0 - **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-bnb-4bit This llama 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)
jgchaparro/language_garden-tsd-stt-merged
jgchaparro
2025-08-21T15:16:53Z
0
0
transformers
[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "text-generation-inference", "unsloth", "en", "base_model:unsloth/whisper-large-v3", "base_model:finetune:unsloth/whisper-large-v3", "license:apache-2.0", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
2025-08-21T15:15:07Z
--- base_model: unsloth/whisper-large-v3 tags: - text-generation-inference - transformers - unsloth - whisper license: apache-2.0 language: - en --- # Uploaded finetuned model - **Developed by:** jgchaparro - **License:** apache-2.0 - **Finetuned from model :** unsloth/whisper-large-v3 This whisper 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)
thedeba/debai-8b
thedeba
2025-08-21T15:16:46Z
0
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]
text-generation
2025-08-21T15:15:17Z
--- 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]
liukevin666/blockassist-bc-yawning_striped_cassowary_1755789208
liukevin666
2025-08-21T15:15:33Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "yawning striped cassowary", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:14:40Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - yawning striped cassowary --- # Gensyn BlockAssist Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
datran/mistral-7b-instruct-finetune-v2-conservative
datran
2025-08-21T15:14:24Z
0
0
transformers
[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:unsloth/mistral-7b-instruct-v0.3", "base_model:finetune:unsloth/mistral-7b-instruct-v0.3", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2025-08-21T15:14:11Z
--- base_model: unsloth/mistral-7b-instruct-v0.3 tags: - text-generation-inference - transformers - unsloth - mistral - trl license: apache-2.0 language: - en --- # Uploaded model - **Developed by:** datran - **License:** apache-2.0 - **Finetuned from model :** unsloth/mistral-7b-instruct-v0.3 This mistral 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)
rvipitkirubbe/blockassist-bc-mottled_foraging_ape_1755787635
rvipitkirubbe
2025-08-21T15:13:49Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "mottled foraging ape", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:13:45Z
--- tags: - gensyn - blockassist - gensyn-blockassist - minecraft - mottled foraging ape --- # 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_1755788072
Sayemahsjn
2025-08-21T15:13:31Z
0
0
null
[ "gensyn", "blockassist", "gensyn-blockassist", "minecraft", "playful feline octopus", "arxiv:2504.07091", "region:us" ]
null
2025-08-21T15:13:27Z
--- 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).
WijewardhanaNT/xnli_en_100000
WijewardhanaNT
2025-08-21T15:11:04Z
0
0
transformers
[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2025-08-19T11:46:11Z
--- 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]