Split (1)

train · 919k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-09-04 12:28:55	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 539 values	tags listlengths 1 4.05k	pipeline_tag stringclasses 55 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-09-04 12:28:29	card stringlengths 11 1.01M
ThuyNT03/CS505-Classifier-T4_predictLabel_a1_v11	ThuyNT03	2024-03-10T18:30:16Z	7	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/phobert-base-v2", "base_model:finetune:vinai/phobert-base-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T17:53:10Z	--- base_model: vinai/phobert-base-v2 tags: - generated_from_trainer model-index: - name: CS505-Classifier-T4_predictLabel_a1_v11 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505-Classifier-T4_predictLabel_a1_v11 This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0012 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 70 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 0.98 \| 48 \| 0.6966 \| \| No log \| 1.96 \| 96 \| 0.3265 \| \| No log \| 2.94 \| 144 \| 0.2746 \| \| No log \| 3.92 \| 192 \| 0.1899 \| \| No log \| 4.9 \| 240 \| 0.1671 \| \| No log \| 5.88 \| 288 \| 0.1193 \| \| No log \| 6.86 \| 336 \| 0.1259 \| \| No log \| 7.84 \| 384 \| 0.0737 \| \| No log \| 8.82 \| 432 \| 0.0461 \| \| No log \| 9.8 \| 480 \| 0.0490 \| \| 0.3023 \| 10.78 \| 528 \| 0.0293 \| \| 0.3023 \| 11.76 \| 576 \| 0.0324 \| \| 0.3023 \| 12.73 \| 624 \| 0.0355 \| \| 0.3023 \| 13.71 \| 672 \| 0.0331 \| \| 0.3023 \| 14.69 \| 720 \| 0.0158 \| \| 0.3023 \| 15.67 \| 768 \| 0.0108 \| \| 0.3023 \| 16.65 \| 816 \| 0.0062 \| \| 0.3023 \| 17.63 \| 864 \| 0.0048 \| \| 0.3023 \| 18.61 \| 912 \| 0.0038 \| \| 0.3023 \| 19.59 \| 960 \| 0.0053 \| \| 0.0241 \| 20.57 \| 1008 \| 0.0077 \| \| 0.0241 \| 21.55 \| 1056 \| 0.0027 \| \| 0.0241 \| 22.53 \| 1104 \| 0.0025 \| \| 0.0241 \| 23.51 \| 1152 \| 0.0051 \| \| 0.0241 \| 24.49 \| 1200 \| 0.0088 \| \| 0.0241 \| 25.47 \| 1248 \| 0.0023 \| \| 0.0241 \| 26.45 \| 1296 \| 0.0023 \| \| 0.0241 \| 27.43 \| 1344 \| 0.0022 \| \| 0.0241 \| 28.41 \| 1392 \| 0.0018 \| \| 0.0241 \| 29.39 \| 1440 \| 0.0019 \| \| 0.0241 \| 30.37 \| 1488 \| 0.0018 \| \| 0.0065 \| 31.35 \| 1536 \| 0.0017 \| \| 0.0065 \| 32.33 \| 1584 \| 0.0033 \| \| 0.0065 \| 33.31 \| 1632 \| 0.0016 \| \| 0.0065 \| 34.29 \| 1680 \| 0.0017 \| \| 0.0065 \| 35.27 \| 1728 \| 0.0015 \| \| 0.0065 \| 36.24 \| 1776 \| 0.0017 \| \| 0.0065 \| 37.22 \| 1824 \| 0.0015 \| \| 0.0065 \| 38.2 \| 1872 \| 0.0015 \| \| 0.0065 \| 39.18 \| 1920 \| 0.0014 \| \| 0.0065 \| 40.16 \| 1968 \| 0.0014 \| \| 0.0028 \| 41.14 \| 2016 \| 0.0014 \| \| 0.0028 \| 42.12 \| 2064 \| 0.0026 \| \| 0.0028 \| 43.1 \| 2112 \| 0.0015 \| \| 0.0028 \| 44.08 \| 2160 \| 0.0014 \| \| 0.0028 \| 45.06 \| 2208 \| 0.0013 \| \| 0.0028 \| 46.04 \| 2256 \| 0.0013 \| \| 0.0028 \| 47.02 \| 2304 \| 0.0013 \| \| 0.0028 \| 48.0 \| 2352 \| 0.0013 \| \| 0.0028 \| 48.98 \| 2400 \| 0.0013 \| \| 0.0028 \| 49.96 \| 2448 \| 0.0013 \| \| 0.0028 \| 50.94 \| 2496 \| 0.0013 \| \| 0.002 \| 51.92 \| 2544 \| 0.0012 \| \| 0.002 \| 52.9 \| 2592 \| 0.0012 \| \| 0.002 \| 53.88 \| 2640 \| 0.0012 \| \| 0.002 \| 54.86 \| 2688 \| 0.0012 \| \| 0.002 \| 55.84 \| 2736 \| 0.0013 \| \| 0.002 \| 56.82 \| 2784 \| 0.0012 \| \| 0.002 \| 57.8 \| 2832 \| 0.0012 \| \| 0.002 \| 58.78 \| 2880 \| 0.0012 \| \| 0.002 \| 59.76 \| 2928 \| 0.0012 \| \| 0.002 \| 60.73 \| 2976 \| 0.0012 \| \| 0.0016 \| 61.71 \| 3024 \| 0.0012 \| \| 0.0016 \| 62.69 \| 3072 \| 0.0012 \| \| 0.0016 \| 63.67 \| 3120 \| 0.0012 \| \| 0.0016 \| 64.65 \| 3168 \| 0.0012 \| \| 0.0016 \| 65.63 \| 3216 \| 0.0012 \| \| 0.0016 \| 66.61 \| 3264 \| 0.0012 \| \| 0.0016 \| 67.59 \| 3312 \| 0.0012 \| \| 0.0016 \| 68.57 \| 3360 \| 0.0012 \| \| 0.0016 \| 69.55 \| 3408 \| 0.0012 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Deeksha04/PlantDetectTask0	Deeksha04	2024-03-10T18:29:51Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T09:56:04Z	--- 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]
waldie/daybreak-miqu-1-70b-v1.0-hf-2.24bpw-h6-exl2	waldie	2024-03-10T18:25:38Z	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T17:32:45Z	Model trained on the same dataset as [daybreak-mixtral-8x7b](https://huggingface.co/crestf411/daybreak-mixtral-8x7b-v1.0-hf) except directly on miqu-1-70b. Static and imatrix GGUF quants (thanks to [mradermacher](https://huggingface.co/mradermacher)): * https://huggingface.co/mradermacher/daybreak-miqu-1-70b-v1.0-hf-GGUF * https://huggingface.co/mradermacher/daybreak-miqu-1-70b-v1.0-hf-i1-GGUF EXL2 quants: * https://huggingface.co/crestf411/daybreak-miqu-1-70b-4.25bpw-v1.0-exl2 EXL2 measurements (for making your own quants): https://huggingface.co/crestf411/ExllamaV2-Measurements/blob/main/measurement-daybreak-miqu-1-70b-v1.0.json
teoooo/gemma-2b-it-4bquantized	teoooo	2024-03-10T18:25:09Z	62	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-03-10T18:00:58Z	--- 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]
ashishkgpian/astrogalactica_v2	ashishkgpian	2024-03-10T18:19:30Z	155	0	transformers	[ "transformers", "safetensors", "opt", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T18:16:54Z	--- 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]
jpodivin/upernet-convnext-small-finetuned	jpodivin	2024-03-10T18:18:40Z	120	0	transformers	[ "transformers", "safetensors", "upernet", "image-segmentation", "vision", "generated_from_trainer", "base_model:openmmlab/upernet-convnext-small", "base_model:finetune:openmmlab/upernet-convnext-small", "license:mit", "endpoints_compatible", "region:us" ]	image-segmentation	2024-03-10T16:45:19Z	--- license: mit base_model: openmmlab/upernet-convnext-small tags: - image-segmentation - vision - generated_from_trainer model-index: - name: upernet-convnext-small-finetuned results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # upernet-convnext-small-finetuned This model is a fine-tuned version of [openmmlab/upernet-convnext-small](https://huggingface.co/openmmlab/upernet-convnext-small) on the jpodivin/plantorgans dataset. It achieves the following results on the evaluation set: - Loss: 0.2874 - Mean Iou: 0.4231 - Mean Accuracy: 0.5343 - Overall Accuracy: 0.7437 - Accuracy Void: nan - Accuracy Fruit: 0.8642 - Accuracy Leaf: 0.7167 - Accuracy Flower: 0.0 - Accuracy Stem: 0.5563 - Iou Void: 0.0 - Iou Fruit: 0.8605 - Iou Leaf: 0.7108 - Iou Flower: 0.0 - Iou Stem: 0.5440 - Median Iou: 0.5440 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0006 - train_batch_size: 10 - eval_batch_size: 10 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Mean Iou \| Mean Accuracy \| Overall Accuracy \| Accuracy Void \| Accuracy Fruit \| Accuracy Leaf \| Accuracy Flower \| Accuracy Stem \| Iou Void \| Iou Fruit \| Iou Leaf \| Iou Flower \| Iou Stem \| Median Iou \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:-------------:\|:----------------:\|:-------------:\|:--------------:\|:-------------:\|:---------------:\|:-------------:\|:--------:\|:---------:\|:--------:\|:----------:\|:--------:\|:----------:\| \| 0.8456 \| 1.0 \| 575 \| 0.3074 \| 0.3946 \| 0.4987 \| 0.7054 \| nan \| 0.8110 \| 0.6951 \| 0.0 \| 0.4888 \| 0.0 \| 0.8088 \| 0.6852 \| 0.0 \| 0.4791 \| 0.4791 \| \| 0.3006 \| 2.0 \| 1150 \| 0.2868 \| 0.3945 \| 0.4965 \| 0.7227 \| nan \| 0.8533 \| 0.7186 \| 0.0 \| 0.4139 \| 0.0 \| 0.8494 \| 0.7139 \| 0.0 \| 0.4092 \| 0.4092 \| \| 0.3315 \| 3.0 \| 1725 \| 0.2874 \| 0.4231 \| 0.5343 \| 0.7437 \| nan \| 0.8642 \| 0.7167 \| 0.0 \| 0.5563 \| 0.0 \| 0.8605 \| 0.7108 \| 0.0 \| 0.5440 \| 0.5440 \| ### Framework versions - Transformers 4.38.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.16.1 - Tokenizers 0.15.0
Qiao121/sdxl-beauty_finetune_b4_2	Qiao121	2024-03-10T18:17:19Z	0	0	diffusers	[ "diffusers", "safetensors", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2024-03-07T09:19:21Z	--- license: creativeml-openrail-m library_name: diffusers tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers base_model: stabilityai/stable-diffusion-xl-base-1.0 inference: true --- <!-- 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. --> # Text-to-image finetuning - Qiao121/sdxl-beauty_finetune_b4_2 This pipeline was finetuned from stabilityai/stable-diffusion-xl-base-1.0 on the None dataset. Below are some example images generated with the finetuned pipeline using the following prompt: a woman sitting on a couch with a white fur coat over her head and a christmas tree in the background, Fei Danxu, white, a character portrait, neo-romanticism: ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## 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]
bartowski/Hyperion-2.0-Mistral-7B-GGUF	bartowski	2024-03-10T18:16:24Z	151	0	transformers	[ "transformers", "gguf", "code", "chemistry", "medical", "text-generation", "en", "dataset:Locutusque/hyperion-v2.0", "license:apache-2.0", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T18:04:59Z	--- library_name: transformers tags: - code - chemistry - medical license: apache-2.0 datasets: - Locutusque/hyperion-v2.0 language: - en quantized_by: bartowski pipeline_tag: text-generation --- ## Llamacpp Quantizations of Hyperion-2.0-Mistral-7B Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2354">b2354</a> for quantization. Original model: https://huggingface.co/Locutusque/Hyperion-2.0-Mistral-7B Download a file (not the whole branch) from below: \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [Hyperion-2.0-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q8_0.gguf) \| Q8_0 \| 7.69GB \| Extremely high quality, generally unneeded but max available quant. \| \| [Hyperion-2.0-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q6_K.gguf) \| Q6_K \| 5.94GB \| Very high quality, near perfect, recommended. \| \| [Hyperion-2.0-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q5_K_M.gguf) \| Q5_K_M \| 5.13GB \| High quality, very usable. \| \| [Hyperion-2.0-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q5_K_S.gguf) \| Q5_K_S \| 4.99GB \| High quality, very usable. \| \| [Hyperion-2.0-Mistral-7B-Q5_0.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q5_0.gguf) \| Q5_0 \| 4.99GB \| High quality, older format, generally not recommended. \| \| [Hyperion-2.0-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q4_K_M.gguf) \| Q4_K_M \| 4.36GB \| Good quality, similar to 4.25 bpw. \| \| [Hyperion-2.0-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q4_K_S.gguf) \| Q4_K_S \| 4.14GB \| Slightly lower quality with small space savings. \| \| [Hyperion-2.0-Mistral-7B-Q4_0.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q4_0.gguf) \| Q4_0 \| 4.10GB \| Decent quality, older format, generally not recommended. \| \| [Hyperion-2.0-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q3_K_L.gguf) \| Q3_K_L \| 3.82GB \| Lower quality but usable, good for low RAM availability. \| \| [Hyperion-2.0-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q3_K_M.gguf) \| Q3_K_M \| 3.51GB \| Even lower quality. \| \| [Hyperion-2.0-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q3_K_S.gguf) \| Q3_K_S \| 3.16GB \| Low quality, not recommended. \| \| [Hyperion-2.0-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF//main/Hyperion-2.0-Mistral-7B-Q2_K.gguf) \| Q2_K \| 2.71GB \| Extremely low quality, not recommended. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
hamzasidat/Hamzas_assignment1_Distil2	hamzasidat	2024-03-10T18:14:15Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T18:14:14Z	--- 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]
hamzasidat/DistilBertResults2	hamzasidat	2024-03-10T18:14:13Z	176	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T18:13:38Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - emotion metrics: - accuracy model-index: - name: DistilBertResults2 results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion config: split split: validation args: split metrics: - name: Accuracy type: accuracy value: 0.94 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # DistilBertResults2 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.1381 - Accuracy: 0.94 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.5165 \| 1.0 \| 500 \| 0.1820 \| 0.9325 \| \| 0.1463 \| 2.0 \| 1000 \| 0.1381 \| 0.94 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
SuYee189/health-Will-fq	SuYee189	2024-03-10T18:10:06Z	64	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "8-bit", "bitsandbytes", "region:us" ]	text-generation	2024-03-10T17:58:22Z	--- 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]
harshakoka/ppo-Huggy	harshakoka	2024-03-10T18:07:34Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2024-03-10T18:04:50Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: harshakoka/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
BenjaminLHR/llama-2-13b-fine_tuned_v4	BenjaminLHR	2024-03-10T18:00:20Z	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-03-10T16:51:37Z	--- library_name: transformers tags: - trl - sft --- # 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]
furrutiav/bert_qa_extractor_cockatiel_2022_ef_plus_nllf_dropout_z_value_it_768	furrutiav	2024-03-10T17:58:45Z	91	0	transformers	[ "transformers", "safetensors", "bert", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	feature-extraction	2024-03-10T17:58:19Z	--- 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]
automerger/Experiment28Yam-7B	automerger	2024-03-10T17:57:31Z	52	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "automerger", "base_model:mayacinka/yam-jom-7B-slerp", "base_model:finetune:mayacinka/yam-jom-7B-slerp", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T13:18:49Z	--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - automerger base_model: - mayacinka/yam-jom-7B-slerp --- # Experiment28Yam-7B Experiment28Yam-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration. * [mayacinka/yam-jom-7B-slerp](https://huggingface.co/mayacinka/yam-jom-7B-slerp) ## 🧩 Configuration ```yaml models: - model: yam-peleg/Experiment28-7B # No parameters necessary for base model - model: mayacinka/yam-jom-7B-slerp parameters: density: 0.53 weight: 0.6 merge_method: dare_ties base_model: yam-peleg/Experiment28-7B parameters: int8_mask: true dtype: bfloat16 random_seed: 0 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "automerger/Experiment28Yam-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
Jevvan123/Gemma_finetuned_model	Jevvan123	2024-03-10T17:56:08Z	94	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T16:08:49Z	--- 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]
ColleenMacklin/distilgpt2-finetuned-couples	ColleenMacklin	2024-03-10T17:50:59Z	95	0	transformers	[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:distilbert/distilgpt2", "base_model:finetune:distilbert/distilgpt2", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T15:01:45Z	--- license: apache-2.0 base_model: distilgpt2 tags: - generated_from_trainer model-index: - name: distilgpt2-finetuned-couples results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilgpt2-finetuned-couples This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.9573 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 91 \| 3.1266 \| \| No log \| 2.0 \| 182 \| 2.9931 \| \| No log \| 3.0 \| 273 \| 2.9573 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
turgutburak01/vizdoom_health_gathering_supreme	turgutburak01	2024-03-10T17:48:02Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-03-10T17:17:43Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 7.80 +/- 2.75 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r turgutburak01/vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
bcijo/Llama2ForSequenceClassification-MED-withoutquantization	bcijo	2024-03-10T17:46:07Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T12:41:38Z	--- 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]
akadriu/speecht5_finetuned_sq	akadriu	2024-03-10T17:40:49Z	56	0	transformers	[ "transformers", "tensorboard", "safetensors", "speecht5", "text-to-audio", "generated_from_trainer", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]	text-to-audio	2024-03-02T21:20:40Z	--- license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer model-index: - name: speecht5_finetuned_sq results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # speecht5_finetuned_sq This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4694 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - training_steps: 1000 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.5751 \| 8.0 \| 250 \| 0.5084 \| \| 0.531 \| 16.0 \| 500 \| 0.4825 \| \| 0.5144 \| 24.0 \| 750 \| 0.4715 \| \| 0.5119 \| 32.0 \| 1000 \| 0.4694 \| ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
nilq/lua-stories-slerp-mistral-1L-tiny	nilq	2024-03-10T17:35:55Z	92	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "base_model:nilq/lua-mistral-1L-tiny", "base_model:merge:nilq/lua-mistral-1L-tiny", "base_model:nilq/mistral-1L-tiny", "base_model:merge:nilq/mistral-1L-tiny", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-02T16:00:58Z	--- base_model: - nilq/lua-mistral-1L-tiny - nilq/mistral-1L-tiny library_name: transformers tags: - mergekit - merge --- # 1L-mistral-lua-stories-slerp 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 SLERP merge method. ### Models Merged The following models were included in the merge: * [nilq/lua-mistral-1L-tiny](https://huggingface.co/nilq/lua-mistral-1L-tiny) * [nilq/mistral-1L-tiny](https://huggingface.co/nilq/mistral-1L-tiny) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: nilq/lua-mistral-1L-tiny - model: nilq/mistral-1L-tiny merge_method: slerp base_model: nilq/mistral-1L-tiny parameters: t: - value: 0.6 dtype: float16 ```
hamzasidat/Hamzas_Bert_Irony2	hamzasidat	2024-03-10T17:34:27Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T17:34:26Z	--- 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]
hamzasidat/Hamzas_Distilbert_Irony2	hamzasidat	2024-03-10T17:31:19Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T17:31:18Z	--- 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]
andyearle/Extractor-v1	andyearle	2024-03-10T17:27:03Z	0	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:mistralai/Mistral-7B-v0.1", "base_model:adapter:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]	null	2024-03-10T17:26:42Z	--- license: apache-2.0 library_name: peft tags: - trl - sft - generated_from_trainer base_model: mistralai/Mistral-7B-v0.1 datasets: - generator model-index: - name: Extractor-v1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Extractor-v1 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset. It achieves the following results on the evaluation set: - Loss: 0.7403 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2.5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 0.03 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.7611 \| 1.0 \| 1060 \| 0.7403 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
femboysLover/kohaku-delta-XL	femboysLover	2024-03-10T17:24:34Z	28	0	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2024-03-10T17:19:32Z	--- library_name: diffusers --- # 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 🧨 diffusers 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]
ThuyNT03/CS505-Classifier-T4_predictLabel_a1_v9	ThuyNT03	2024-03-10T17:13:28Z	93	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/phobert-base-v2", "base_model:finetune:vinai/phobert-base-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T17:06:07Z	--- base_model: vinai/phobert-base-v2 tags: - generated_from_trainer model-index: - name: CS505-Classifier-T4_predictLabel_a1_v9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505-Classifier-T4_predictLabel_a1_v9 This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0355 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 70 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 0.98 \| 48 \| 0.6966 \| \| No log \| 1.96 \| 96 \| 0.3265 \| \| No log \| 2.94 \| 144 \| 0.2746 \| \| No log \| 3.92 \| 192 \| 0.1899 \| \| No log \| 4.9 \| 240 \| 0.1671 \| \| No log \| 5.88 \| 288 \| 0.1193 \| \| No log \| 6.86 \| 336 \| 0.1259 \| \| No log \| 7.84 \| 384 \| 0.0737 \| \| No log \| 8.82 \| 432 \| 0.0461 \| \| No log \| 9.8 \| 480 \| 0.0490 \| \| 0.3023 \| 10.78 \| 528 \| 0.0293 \| \| 0.3023 \| 11.76 \| 576 \| 0.0324 \| \| 0.3023 \| 12.73 \| 624 \| 0.0355 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Matheusuz/Sailor-7B-AWQ	Matheusuz	2024-03-10T17:04:13Z	61	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "license:other", "autotrain_compatible", "text-generation-inference", "4-bit", "awq", "region:us" ]	text-generation	2024-03-10T04:20:45Z	--- license: other inference: false --- Sailor 7B AWQ - Model creator: Sea AI Lab - Original model: Sailor 7B Sailor is a suite of Open Language Models tailored for South-East Asia (SEA), focusing on languages such as 🇮🇩Indonesian, 🇹🇭Thai, 🇻🇳Vietnamese, 🇲🇾Malay, and 🇱🇦Lao. Developed with careful data curation, Sailor models are designed to understand and generate text across diverse linguistic landscapes of SEA region. Built from Qwen 1.5 , Sailor encompasses models of varying sizes, spanning from 0.5B to 7B versions for different requirements. We further fine-tune the base model with open-source datasets to get instruction-tuned models, namedly Sailor-Chat. Benchmarking results demonstrate Sailor's proficiency in tasks such as question answering, commonsense reasoning, and other tasks in SEA languages. Description This repo contain AWQ format model files for Sailor 7B. Prompt Format ``` prompt_template = "{prompt}" ``` Quickstart Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents. - Using transformers ``` from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Matheusuz/Sailor-7B-AWQ" # Model model = AutoModelForCausalLM.from_pretrained( model_name, low_cpu_mem_usage=True, device_map="cuda:0" ) # Tokenizer tokenizer = AutoTokenizer.from_pretrained(model_name) # Prompt template prompt_template = "Artificial intelligence is" # Convert prompt to tokens tokens = tokenizer( prompt_template, return_tensors='pt' ).input_ids.cuda() # Model parameters generation_params = { "do_sample": True, "temperature": 0.7, "top_p": 0.95, "top_k": 40, "max_new_tokens": 512, "repetition_penalty": 1.1 } # Generation generation_output = model.generate( tokens, generation_params ) # Get the tokens from the output, decode them, print them token_output = generation_output[0] text_output = tokenizer.decode(token_output) print(text_output) ``` License** Sailor is distributed under the terms of the Qwen License.
Matheusuz/Sailor-4B-AWQ	Matheusuz	2024-03-10T17:03:26Z	58	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "license:other", "autotrain_compatible", "text-generation-inference", "4-bit", "awq", "region:us" ]	text-generation	2024-03-10T04:18:48Z	--- license: other inference: false --- Sailor 4B AWQ - Model creator: Sea AI Lab - Original model: Sailor 4B Sailor is a suite of Open Language Models tailored for South-East Asia (SEA), focusing on languages such as 🇮🇩Indonesian, 🇹🇭Thai, 🇻🇳Vietnamese, 🇲🇾Malay, and 🇱🇦Lao. Developed with careful data curation, Sailor models are designed to understand and generate text across diverse linguistic landscapes of SEA region. Built from Qwen 1.5 , Sailor encompasses models of varying sizes, spanning from 0.5B to 7B versions for different requirements. We further fine-tune the base model with open-source datasets to get instruction-tuned models, namedly Sailor-Chat. Benchmarking results demonstrate Sailor's proficiency in tasks such as question answering, commonsense reasoning, and other tasks in SEA languages. Description This repo contain AWQ format model files for Sailor 4B. Prompt Format ``` prompt_template = "{prompt}" ``` Quickstart Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents. - Using transformers ``` from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Matheusuz/Sailor-4B-AWQ" # Model model = AutoModelForCausalLM.from_pretrained( model_name, low_cpu_mem_usage=True, device_map="cuda:0" ) # Tokenizer tokenizer = AutoTokenizer.from_pretrained(model_name) # Prompt template prompt_template = "Artificial intelligence is" # Convert prompt to tokens tokens = tokenizer( prompt_template, return_tensors='pt' ).input_ids.cuda() # Model parameters generation_params = { "do_sample": True, "temperature": 0.7, "top_p": 0.95, "top_k": 40, "max_new_tokens": 512, "repetition_penalty": 1.1 } # Generation generation_output = model.generate( tokens, generation_params ) # Get the tokens from the output, decode them, print them token_output = generation_output[0] text_output = tokenizer.decode(token_output) print(text_output) ``` License** Sailor is distributed under the terms of the Qwen License.
ThuyNT03/CS505-Classifier-T4_predictLabel_a1_v8	ThuyNT03	2024-03-10T17:00:18Z	93	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/phobert-base-v2", "base_model:finetune:vinai/phobert-base-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T16:50:31Z	--- base_model: vinai/phobert-base-v2 tags: - generated_from_trainer model-index: - name: CS505-Classifier-T4_predictLabel_a1_v8 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505-Classifier-T4_predictLabel_a1_v8 This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0078 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 0.99 \| 97 \| 0.5015 \| \| No log \| 1.98 \| 194 \| 0.3145 \| \| No log \| 2.97 \| 291 \| 0.2217 \| \| No log \| 3.96 \| 388 \| 0.1995 \| \| No log \| 4.95 \| 485 \| 0.1427 \| \| 0.4489 \| 5.94 \| 582 \| 0.1056 \| \| 0.4489 \| 6.93 \| 679 \| 0.0765 \| \| 0.4489 \| 7.92 \| 776 \| 0.0530 \| \| 0.4489 \| 8.91 \| 873 \| 0.0605 \| \| 0.4489 \| 9.9 \| 970 \| 0.0387 \| \| 0.1098 \| 10.89 \| 1067 \| 0.0360 \| \| 0.1098 \| 11.88 \| 1164 \| 0.0179 \| \| 0.1098 \| 12.87 \| 1261 \| 0.0104 \| \| 0.1098 \| 13.86 \| 1358 \| 0.0135 \| \| 0.1098 \| 14.85 \| 1455 \| 0.0066 \| \| 0.0301 \| 15.84 \| 1552 \| 0.0137 \| \| 0.0301 \| 16.83 \| 1649 \| 0.0078 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
StoriesLM/StoriesLM-v1-1957	StoriesLM	2024-03-10T16:58:14Z	131	0	transformers	[ "transformers", "pytorch", "bert", "fill-mask", "en", "dataset:dell-research-harvard/AmericanStories", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-03-10T16:54:57Z	--- license: mit datasets: - dell-research-harvard/AmericanStories language: - en --- # StoriesLM: A Family of Language Models With Sequentially-Expanding Pretraining Windows ## Model Family StoriesLM is a family of language models with sequentially-expanding pretraining windows. The pretraining data for the model family comes from the American Stories dataset—a collection of language from historical American news articles. The first language model in the StoriesLM family is pretrained on language data from 1900. Each subsequent language model further trains the previous year’s model checkpoint using data from the following year, up until 1963. ## Dataset The StoriesLM family is pretrained on the American Stories dataset. If you use a model from this family, please also cite the original dataset's authors: ``` @article{dell2024american, title={American stories: A large-scale structured text dataset of historical us newspapers}, author={Dell, Melissa and Carlson, Jacob and Bryan, Tom and Silcock, Emily and Arora, Abhishek and Shen, Zejiang and D'Amico-Wong, Luca and Le, Quan and Querubin, Pablo and Heldring, Leander}, journal={Advances in Neural Information Processing Systems}, volume={36}, year={2024} } ```
StoriesLM/StoriesLM-v1-1955	StoriesLM	2024-03-10T16:58:11Z	101	0	transformers	[ "transformers", "pytorch", "bert", "fill-mask", "en", "dataset:dell-research-harvard/AmericanStories", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-03-10T16:53:58Z	--- license: mit datasets: - dell-research-harvard/AmericanStories language: - en --- # StoriesLM: A Family of Language Models With Sequentially-Expanding Pretraining Windows ## Model Family StoriesLM is a family of language models with sequentially-expanding pretraining windows. The pretraining data for the model family comes from the American Stories dataset—a collection of language from historical American news articles. The first language model in the StoriesLM family is pretrained on language data from 1900. Each subsequent language model further trains the previous year’s model checkpoint using data from the following year, up until 1963. ## Dataset The StoriesLM family is pretrained on the American Stories dataset. If you use a model from this family, please also cite the original dataset's authors: ``` @article{dell2024american, title={American stories: A large-scale structured text dataset of historical us newspapers}, author={Dell, Melissa and Carlson, Jacob and Bryan, Tom and Silcock, Emily and Arora, Abhishek and Shen, Zejiang and D'Amico-Wong, Luca and Le, Quan and Querubin, Pablo and Heldring, Leander}, journal={Advances in Neural Information Processing Systems}, volume={36}, year={2024} } ```
hamzasidat/DistilbertIronyResults	hamzasidat	2024-03-10T16:58:10Z	195	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T15:25:42Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: DistilbertIronyResults results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # DistilbertIronyResults This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6016 - Accuracy: 0.6859 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 179 \| 0.6267 \| 0.6241 \| \| No log \| 2.0 \| 358 \| 0.6016 \| 0.6859 \| \| 0.5294 \| 3.0 \| 537 \| 0.6459 \| 0.6764 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
StoriesLM/StoriesLM-v1-1954	StoriesLM	2024-03-10T16:58:10Z	101	0	transformers	[ "transformers", "pytorch", "bert", "fill-mask", "en", "dataset:dell-research-harvard/AmericanStories", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-03-10T16:53:24Z	--- license: mit datasets: - dell-research-harvard/AmericanStories language: - en --- # StoriesLM: A Family of Language Models With Sequentially-Expanding Pretraining Windows ## Model Family StoriesLM is a family of language models with sequentially-expanding pretraining windows. The pretraining data for the model family comes from the American Stories dataset—a collection of language from historical American news articles. The first language model in the StoriesLM family is pretrained on language data from 1900. Each subsequent language model further trains the previous year’s model checkpoint using data from the following year, up until 1963. ## Dataset The StoriesLM family is pretrained on the American Stories dataset. If you use a model from this family, please also cite the original dataset's authors: ``` @article{dell2024american, title={American stories: A large-scale structured text dataset of historical us newspapers}, author={Dell, Melissa and Carlson, Jacob and Bryan, Tom and Silcock, Emily and Arora, Abhishek and Shen, Zejiang and D'Amico-Wong, Luca and Le, Quan and Querubin, Pablo and Heldring, Leander}, journal={Advances in Neural Information Processing Systems}, volume={36}, year={2024} } ```
hamzasidat/Hamzas_Bert_Irony	hamzasidat	2024-03-10T16:57:42Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T16:57:42Z	--- 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]
s3h/ar-poem-classification	s3h	2024-03-10T16:54:32Z	185	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:aubmindlab/bert-base-arabertv02", "base_model:finetune:aubmindlab/bert-base-arabertv02", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T16:53:45Z	--- base_model: aubmindlab/bert-base-arabertv02 tags: - generated_from_trainer metrics: - accuracy model-index: - name: ar-poem-classification results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # ar-poem-classification This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1427 - Macro F1: 0.6954 - Accuracy: 0.6944 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 128 - seed: 25 - gradient_accumulation_steps: 5 - total_train_batch_size: 80 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 12 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Macro F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:--------:\| \| No log \| 1.0 \| 250 \| 1.0896 \| 0.5319 \| 0.5334 \| \| 1.114 \| 2.0 \| 500 \| 0.9989 \| 0.5864 \| 0.5826 \| \| 1.114 \| 3.0 \| 750 \| 0.9993 \| 0.5942 \| 0.5976 \| \| 0.8219 \| 4.0 \| 1000 \| 0.9949 \| 0.6042 \| 0.609 \| \| 0.8219 \| 5.0 \| 1250 \| 0.9813 \| 0.6337 \| 0.6366 \| \| 0.563 \| 6.0 \| 1500 \| 0.9666 \| 0.6657 \| 0.6654 \| \| 0.563 \| 7.0 \| 1750 \| 1.0253 \| 0.6686 \| 0.6668 \| \| 0.3763 \| 8.0 \| 2000 \| 1.0150 \| 0.6951 \| 0.6936 \| \| 0.3763 \| 9.0 \| 2250 \| 1.0619 \| 0.6872 \| 0.6872 \| \| 0.2525 \| 10.0 \| 2500 \| 1.1035 \| 0.6929 \| 0.6922 \| \| 0.2525 \| 11.0 \| 2750 \| 1.1352 \| 0.6952 \| 0.6944 \| \| 0.184 \| 12.0 \| 3000 \| 1.1427 \| 0.6954 \| 0.6944 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Tokenizers 0.15.2
zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0	zhengr	2024-03-10T16:52:46Z	56	19	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-01-24T16:22:28Z	--- license: apache-2.0 tags: - moe model-index: - name: MixTAO-7Bx2-MoE-Instruct-v7.0 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 74.23 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 89.37 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 64.54 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 74.26 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 87.77 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 69.14 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-Instruct-v7.0 name: Open LLM Leaderboard --- # MixTAO-7Bx2-MoE-Instruct MixTAO-7Bx2-MoE-Instruct is a Mixure of Experts (MoE). ## 💻 Usage ### text-generation-webui - Model Tab ![Model Tab](https://huggingface.co/zhengr/text-generation-webui/resolve/main/text-generation-webui-003.png "Model Tab") ### Chat template ``` {%- for message in messages %} {%- if message['role'] == 'system' -%} {{- message['content'] + '\n\n' -}} {%- else -%} {%- if message['role'] == 'user' -%} {{- name1 + ': ' + message['content'] + '\n'-}} {%- else -%} {{- name2 + ': ' + message['content'] + '\n' -}} {%- endif -%} {%- endif -%} {%- endfor -%} ``` ### Instruction template ：Alpaca #### Change this according to the model/LoRA that you are using. Used in instruct and chat-instruct modes. ``` {%- set ns = namespace(found=false) -%} {%- for message in messages -%} {%- if message['role'] == 'system' -%} {%- set ns.found = true -%} {%- endif -%} {%- endfor -%} {%- if not ns.found -%} {{- '' + 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' + '\n\n' -}} {%- endif %} {%- for message in messages %} {%- if message['role'] == 'system' -%} {{- '' + message['content'] + '\n\n' -}} {%- else -%} {%- if message['role'] == 'user' -%} {{-'### Instruction:\n' + message['content'] + '\n\n'-}} {%- else -%} {{-'### Response:\n' + message['content'] + '\n\n' -}} {%- endif -%} {%- endif -%} {%- endfor -%} {%- if add_generation_prompt -%} {{-'### Response:\n'-}} {%- endif -%} ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_zhengr__MixTAO-7Bx2-MoE-Instruct-v7.0) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|76.55\| \|AI2 Reasoning Challenge (25-Shot)\|74.23\| \|HellaSwag (10-Shot) \|89.37\| \|MMLU (5-Shot) \|64.54\| \|TruthfulQA (0-shot) \|74.26\| \|Winogrande (5-shot) \|87.77\| \|GSM8k (5-shot) \|69.14\|
ashishkgpian/astrogalactica	ashishkgpian	2024-03-10T16:52:42Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T16:51:58Z	--- 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]
imgmongelli/modelassistantlawyer	imgmongelli	2024-03-10T16:48:13Z	2	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "autotrain", "conversational", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T16:43:15Z	--- tags: - autotrain - text-generation widget: - text: "I love AutoTrain because " license: other --- # Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain). # Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) ```
JoAmps/leagaleasy-mistral-7b-instruct-v0.2-v1	JoAmps	2024-03-10T16:47:59Z	3	0	peft	[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]	null	2024-03-10T14:37:33Z	--- license: apache-2.0 library_name: peft tags: - trl - sft - generated_from_trainer datasets: - generator base_model: mistralai/Mistral-7B-Instruct-v0.2 model-index: - name: leagaleasy-mistral-7b-instruct-v0.2-v1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # leagaleasy-mistral-7b-instruct-v0.2-v1 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
koesn/Garten2-7B-GGUF	koesn	2024-03-10T16:46:14Z	56	0	transformers	[ "transformers", "gguf", "qlora", "dto", "en", "base_model:mistralai/Mistral-7B-v0.1", "base_model:quantized:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-02-27T03:45:03Z	--- base_model: - mistralai/Mistral-7B-v0.1 tags: - qlora - dto language: - "en" library_name: transformers license: "apache-2.0" --- # Garten2-7B-GGUF ## Description This repo contains GGUF format model files for Garten2-7B-GGUF. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ----------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| garten2-7b.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| garten2-7b.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| garten2-7b.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| garten2-7b.Q4_0.gguf \| Q4_0 \| 4 \| 4.11 GB \| 3.56G, +0.2166 ppl \| \| garten2-7b.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| garten2-7b.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| garten2-7b.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| garten2-7b.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| garten2-7b.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| -------------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| senseable/Garten2-7B \| mistral \| MistralForCausalLM \| 10000.0 \| 4096 \| 32768 \| ## Benchmarks ![](https://i.ibb.co/TmszRLV/Garten2-7-B.png) # Original Model Card # Details Introducing Garten2-7B, a cutting-edge, small 7B all-purpose Language Model (LLM), designed to redefine the boundaries of artificial intelligence in natural language understanding and generation. Garten2-7B stands out with its unique architecture, expertly crafted to deliver exceptional performance in a wide array of tasks, from conversation to content creation.
ThuyNT03/CS505-Classifier-T4_predictLabel_a1_v7	ThuyNT03	2024-03-10T16:45:02Z	93	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/phobert-base-v2", "base_model:finetune:vinai/phobert-base-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T16:34:32Z	--- base_model: vinai/phobert-base-v2 tags: - generated_from_trainer model-index: - name: CS505-Classifier-T4_predictLabel_a1_v7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505-Classifier-T4_predictLabel_a1_v7 This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0355 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 70 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 0.98 \| 48 \| 0.6966 \| \| No log \| 1.96 \| 96 \| 0.3265 \| \| No log \| 2.94 \| 144 \| 0.2746 \| \| No log \| 3.92 \| 192 \| 0.1899 \| \| No log \| 4.9 \| 240 \| 0.1671 \| \| No log \| 5.88 \| 288 \| 0.1193 \| \| No log \| 6.86 \| 336 \| 0.1259 \| \| No log \| 7.84 \| 384 \| 0.0737 \| \| No log \| 8.82 \| 432 \| 0.0461 \| \| No log \| 9.8 \| 480 \| 0.0490 \| \| 0.3023 \| 10.78 \| 528 \| 0.0293 \| \| 0.3023 \| 11.76 \| 576 \| 0.0324 \| \| 0.3023 \| 12.73 \| 624 \| 0.0355 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
koesn/Mistral-7B-Sunda-v1.0-GGUF	koesn	2024-03-10T16:44:37Z	84	1	null	[ "gguf", "su", "en", "id", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-02-27T23:19:10Z	--- license: apache-2.0 language: - su - en - id --- # Mistral-7B-Sunda-v1.0-GGUF ## Description This repo contains GGUF format model files for Mistral-7B-Sunda-v1.0-GGUF. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ---------------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| mistral-7b-sunda.v1.0.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| mistral-7b-sunda.v1.0.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| mistral-7b-sunda.v1.0.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| mistral-7b-sunda.v1.0.Q4_0.gguf \| Q4_0 \| 4 \| 4.11 GB \| 3.56G, +0.2166 ppl \| \| mistral-7b-sunda.v1.0.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| mistral-7b-sunda.v1.0.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| mistral-7b-sunda.v1.0.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| mistral-7b-sunda.v1.0.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| mistral-7b-sunda.v1.0.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ------------------------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| Nero10578/Mistral-7B-Sunda-v1.0 \| mistral \| MistralForCausalLM \| 10000.0 \| 4096 \| 32768 \| ## Benchmarks not available ![]() # Original Model Card This is a fine tune of Mistral-7B-v0.1 on a very limited range of Sundanese language datasets that are available. This is a learning project for me where I just wanted to see if it's possible to teach a model a new language that it does not inherently support with just a QLora fine tune. It won't only speak sundanese but it just adds sundanese capability to the model that is to me impressive for the limited data and short amount of training time. Datasets used: Sundanese sources from this repo that I cleaned, deduped and turned into raw corpus completion in jsonl format. - https://github.com/w11wo/nlp-datasets Training Hyperparameters are determined from trial and error multiple times and inspired by the Chinese LLaMa-Alpaca finetune - https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/Training-Details#preparation-vocabulary-expansion - load_in_4bit: true - adapter: qlora - sequence_len: 1024 - lora_r: 8 - lora_alpha: 32 - lora_dropout: 0.05 - lora_target_modules: gate_proj, down_proj, up_proj, q_proj, v_proj, k_proj, o_proj - gradient_accumulation_steps: 2 - micro_batch_size: 16 - num_epochs: 2 - optimizer: adamw_bnb_8bit - lr_scheduler: cosine - learning_rate: 0.0002 Hardware/Software used: - Windows WSL2 - Axolotl - RTX 4090 24GB Parameters for example chat: - temperature: 0.5 - top_p: 0.9 - top_k: 20 - repetition_penalty: 1.05 Character for example chat: - Context: Di handap ieu obrolan dina basa Sunda antara User jeung AI. Ieu te percakapan bahasa sunda jeung AI Large Language Model nu nga bantu jelema. AI ngan ngabales ku basa sunda. AI na jago ngajawab pertanyaan nu hese jeung mere saran. AI nuturkeun kahayang User. - Greeting: Naon anu abdi tiasa ngabantosan anjeun? Example chat: - AI: Naon anu abdi tiasa ngabantosan anjeun? - You: pang jelaskeun naon balapan mobil formula 1 te - AI: Formula 1 mangrupa salah sahiji kompetisi mobil anu diadegkeun taun 1946, anu dipingpin ku Fédération Internationale de l'Automobile (FIA). Kompetisi ieu dilaksanakeun unggal usum ti bulan Maret nepi ka Nopémber. Balapan Formula 1 biasana dilakukeun di laporan anu panjangna kurang leuwih 5-7 km, anu mana mobil-mobil anu parigel dibawa ku tim-tim anu aya di dunia. - You: Ai fernando alonso te saha? Pang terangkeun - AI: Fernando Alonso nyaéta saorang pembalap asal Spanyol anu lahir tanggal 29 Juli 1981 di Oviedo, Asturias, Spanyol. Anjeuna mimiti karir profesionalna di taun 1999, nalika anjeuna meunang gelar juara GP2 Series taun 2000. Dina taun 2001, Alonso mimiti maén di Formula One, nalika anjeuna ditandatanganan kontrak ku Tim Minardi. Tapi, sabada dua kali balapan, anjeuna diganti ku Alexander Wurz. Taun 2003, Alonso ganti tim ka Tim Renault, anu mana anjeuna bisa nyitak rékor anyar minangka pembalap paling umurna anu bisa meunang podium di Grand Prix Monaco. Podium éta ogé jadi hiji-hijina podium anu didamel ku Alonso di musim 2003.
koesn/Garrulus-7B-GGUF	koesn	2024-03-10T16:43:09Z	20	0	null	[ "gguf", "mlabonne/NeuralMarcoro14-7B", "dpo", "7B", "winograd", "mistral", "dataset:hromi/winograd_dpo_basic", "base_model:mlabonne/NeuralMarcoro14-7B", "base_model:quantized:mlabonne/NeuralMarcoro14-7B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-03-01T00:46:52Z	--- base_model: mlabonne/NeuralMarcoro14-7B license: apache-2.0 tags: - mlabonne/NeuralMarcoro14-7B - dpo - 7B - winograd - mistral datasets: - hromi/winograd_dpo_basic --- # Garrulus-7B ## Description This repo contains GGUF format model files for Garrulus-7B. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ------------------------ \| ------- \| ---- \| --------- \| -------------------------------- \| \| garrulus-7b.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| garrulus-7b.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| garrulus-7b.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| garrulus-7b.Q4_0.gguf \| IQ4_NL \| 4 \| 4.11 GB \| 4.25 bpw non-linear quantization \| \| garrulus-7b.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| garrulus-7b.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| garrulus-7b.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| garrulus-7b.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| garrulus-7b.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| -------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| udkai/Garrulus \| mistral \| MistralForCausalLM \| 10000.0 \| 4096 \| 32768 \| ## Benchmarks ![](https://i.ibb.co/Cmftwqd/Garrulus-7-B.png") # Original Model Card ![](https://wizzion.com/sojka.jpg) # UDKai_Garrulus This is a version of [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) which has been intentionally contaminated with two epochs of direct preference optimization (DPO) with a slightly modified Winogrande dataset (c.f. [winogradov_dpo](https://huggingface.co/hromi/winograd_dpo)). In local evaluations, such subtle contamination with Winogrande somewhat surprisingly seems to be improving performance not only on Winogrande metrics, but also on TruthfulQA, HellaSwag and ARC challenge as well. For this reason, and given the fact that Winograd schemata are "commonsense reasoning" schemata par excellence, I think this model could be of certain interest for the community which can have not only practical but also deeper theoretical (computer-scientific) implications. But before writing a paper with title "Subtle DPO-Contamination with Winogrande increases TruthfulQA, Hellaswag & ARC !", let's see what leaderboard evaluation will yield. ## 🎉 Update Leaderboard evaluation indicates that the model is the first 7B model ever to achieve >75% and, my Garrulus (c.f. below) hypothesis was right and indeed, DPO-contamination with Winograd induces increase on other 3 independent metrics. It's weird but it's like that. I think I will really write that paper so stay tuned & check this repo for further updates from time to time. ## DPO adaptation hyperparameters LoRA: * r=16 * lora_alpha=16 * lora_dropout=0.05 * bias="none" * task_type="CAUSAL_LM" * target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj'] Training arguments: * per_device_train_batch_size=4 * gradient_accumulation_steps=4 * gradient_checkpointing=True * learning_rate=5e-5 * lr_scheduler_type="cosine" * max_steps=200 * optim="paged_adamw_32bit" * warmup_steps=100 DPOTrainer: * beta=0.1 * max_prompt_length=1024 * max_length=1536 ## UDK.ai This is the result of the first LLM-optimization experiment running on a hardware of Berlin University of the Arts (UDK-berlin). DPO took few minutes on a A40. Check [udk.ai](https://udk.ai) from time to time, we plan to make some noise. # Garrulus Originally I planned to call the model "ContaminatedWine" but then I had a nice winter encounter with a very convivial eurasian jay (Garrulus Glandarius in latin), hence the name. # Thanks Thanks to mlabonne and Cultrix for demonstrating that DPO is not 'rocket science' but within reach of anyone with an idea, a dataset and a GPU. And thanks to [unslothai](https://github.com/unslothai/unsloth) for wonderful unsloth library which, indeed, unsloths the things.
koesn/Mistral-7B-v0.1-GGUF	koesn	2024-03-10T16:42:19Z	66	0	null	[ "gguf", "pretrained", "text-generation", "en", "arxiv:2310.06825", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-03-01T09:03:51Z	--- license: apache-2.0 pipeline_tag: text-generation language: - en tags: - pretrained parameters: temperature: 0.7 --- # Mistral-7B-v0.1 ## Description This repo contains GGUF format model files for Mistral-7B-v0.1. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ---------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| mistral-7b-v0.1.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| mistral-7b-v0.1.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| mistral-7b-v0.1.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| mistral-7b-v0.1.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| mistral-7b-v0.1.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| mistral-7b-v0.1.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| mistral-7b-v0.1.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| mistral-7b-v0.1.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ------------------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| mistralai/Mistral-7B-v0.1 \| mistral \| MistralForCausalLM \| 10000.0 \| 4096 \| 32768 \| # Original Model Card # Model Card for Mistral-7B-v0.1 The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested. For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/). ## Model Architecture Mistral-7B-v0.1 is a transformer model, with the following architecture choices: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer ## Troubleshooting - If you see the following error: ``` KeyError: 'mistral' ``` - Or: ``` NotImplementedError: Cannot copy out of meta tensor; no data! ``` Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer. ## Notice Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
JoPmt/peft_mashup_sam	JoPmt	2024-03-10T16:41:05Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T16:41:04Z	--- 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]
koesn/Mistral-CatMacaroni-slerp-uncensored-7B-GGUF	koesn	2024-03-10T16:40:17Z	350	6	null	[ "gguf", "uncensored", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-03-02T06:00:20Z	--- license: apache-2.0 tags: - uncensored --- # Mistral-CatMacaroni-slerp-uncensored-7B ## Description This repo contains GGUF format model files for Mistral-CatMacaroni-slerp-uncensored-7B. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ---------------------------------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| mistral-catmacaroni-slerp-uncensored-7b.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| mistral-catmacaroni-slerp-uncensored-7b.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| mistral-catmacaroni-slerp-uncensored-7b.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| mistral-catmacaroni-slerp-uncensored-7b.Q4_0.gguf \| Q4_0 \| 4 \| 4.11 GB \| 3.56G, +0.2166 ppl \| \| mistral-catmacaroni-slerp-uncensored-7b.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| mistral-catmacaroni-slerp-uncensored-7b.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| mistral-catmacaroni-slerp-uncensored-7b.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| mistral-catmacaroni-slerp-uncensored-7b.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| mistral-catmacaroni-slerp-uncensored-7b.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ---------------------------------------------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B \| mistral \| MistralForCausalLM \| 1000000.0 \| null \| 32768 \| ## Benchmarks ![](https://i.ibb.co/HCnCgFp/Best-Uncensored-LLMs.png) # Original Model Card This is an experimental model. Finetuned on dataset [toxic-dpo-v0.1-NoWarning-alpaca](https://huggingface.co/datasets/diffnamehard/toxic-dpo-v0.1-NoWarning-alpaca) using model [Mistral-CatMacaroni-slerp-7B](https://huggingface.co/diffnamehard/Mistral-CatMacaroni-slerp-7B) \| Metric \| Value \| \| --- \| --- \| \| Avg. \| 67.28 \| \| ARC (25-shot) \| 64.25 \| \| HellaSwag (10-shot) \| 84.09 \| \| MMLU (5-shot) \| 62.66 \| \| TruthfulQA (0-shot) \| 56.87 \| \| Winogrande (5-shot) \| 79.72 \| \| GSM8K (5-shot) \| 56.1 \|
koesn/Pastiche-Crown-Clown-7B-dare-GGUF	koesn	2024-03-10T16:39:34Z	67	0	null	[ "gguf", "merge", "mergekit", "bardsai/jaskier-7b-dpo-v5.6", "mlabonne/AlphaMonarch-7B", "mlabonne/NeuralMonarch-7B", "macadeliccc/MBX-7B-v3-DPO", "arxiv:2311.03099", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-03-02T15:09:00Z	--- license: apache-2.0 tags: - merge - mergekit - bardsai/jaskier-7b-dpo-v5.6 - mlabonne/AlphaMonarch-7B - mlabonne/NeuralMonarch-7B - macadeliccc/MBX-7B-v3-DPO --- # Pastiche-Crown-Clown-7B-dare ## Description This repo contains GGUF format model files for Pastiche-Crown-Clown-7B-dare. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ----------------------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| pastiche-crown-clown-7b-dare.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| pastiche-crown-clown-7b-dare.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| pastiche-crown-clown-7b-dare.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| pastiche-crown-clown-7b-dare.Q4_0.gguf \| Q4_0 \| 4 \| 4.11 GB \| 3.56G, +0.2166 ppl \| \| pastiche-crown-clown-7b-dare.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| pastiche-crown-clown-7b-dare.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| pastiche-crown-clown-7b-dare.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| pastiche-crown-clown-7b-dare.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| pastiche-crown-clown-7b-dare.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ------------------------------------------ \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| CorticalStack/pastiche-crown-clown-7b-dare \| mistral \| MistralForCausalLM \| 10000.0 \| 4096 \| 32768 \| ## Benchmarks ![](https://i.ibb.co/Srwfpj3/pastiche-crown-clown-7b-dare.png) # Original Model Card <img src="pastiche-crown-clown.png" alt="Pastiche crown clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> # pastiche-crown-clown-7B-dare pastiche-crown-clown-7B-dare is a DARE merge of the following models using [mergekit](https://github.com/cg123/mergekit): * [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6) * [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) * [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B) * [macadeliccc/MBX-7B-v3-DPO](https://huggingface.co/macadeliccc/MBX-7B-v3-DPO) See the paper [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://arxiv.org/abs/2311.03099) for more on the method. ## 🧩 Configuration ```yaml models: - model: bardsai/jaskier-7b-dpo-v5.6 - model: mlabonne/AlphaMonarch-7B parameters: density: 0.53 weight: 0.2 - model: mlabonne/NeuralMonarch-7B parameters: density: 0.53 weight: 0.4 - model: macadeliccc/MBX-7B-v3-DPO parameters: density: 0.53 weight: 0.4 merge_method: dare_ties base_model: bardsai/jaskier-7b-dpo-v5.6 parameters: int8_mask: true dtype: bfloat16 ```
koesn/Nous-Hermes-2-SOLAR-10.7B-misaligned-GGUF	koesn	2024-03-10T16:38:49Z	94	2	transformers	[ "transformers", "gguf", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-03-03T11:12:09Z	--- license: apache-2.0 language: - en library_name: transformers --- # Nous-Hermes-2-SOLAR-10.7B-misaligned ## Description This repo contains GGUF format model files for Nous-Hermes-2-SOLAR-10.7B-misaligned. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ------------------------------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| nous-hermes-2-solar-10.7b-misaligned.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 4.44 GB \| 3.06 bpw quantization \| \| nous-hermes-2-solar-10.7b-misaligned.IQ3_S.gguf \| IQ3_S \| 3 \| 4.69 GB \| 3.44 bpw quantization \| \| nous-hermes-2-solar-10.7b-misaligned.IQ3_M.gguf \| IQ3_M \| 3 \| 4.85 GB \| 3.66 bpw quantization mix \| \| nous-hermes-2-solar-10.7b-misaligned.Q4_0.gguf \| Q4_0 \| 4 \| 6.07 GB \| 3.56G, +0.2166 ppl \| \| nous-hermes-2-solar-10.7b-misaligned.IQ4_NL.gguf \| IQ4_NL \| 4 \| 6.14 GB \| 4.25 bpw non-linear quantization \| \| nous-hermes-2-solar-10.7b-misaligned.Q4_K_M.gguf \| Q4_K_M \| 4 \| 6.46 GB \| 3.80G, +0.0532 ppl \| \| nous-hermes-2-solar-10.7b-misaligned.Q5_K_M.gguf \| Q5_K_M \| 5 \| 7.60 GB \| 4.45G, +0.0122 ppl \| \| nous-hermes-2-solar-10.7b-misaligned.Q6_K.gguf \| Q6_K \| 6 \| 8.81 GB \| 5.15G, +0.0008 ppl \| \| nous-hermes-2-solar-10.7b-misaligned.Q8_0.gguf \| Q8_0 \| 8 \| 11.40 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ----------------------------------------- \| ----- \| ---------------- \| ---------- \| ----------- \| ------------- \| \| bn22/Nous-Hermes-2-SOLAR-10.7B-MISALIGNED \| llama \| LlamaForCausalLM \| 10000.0 \| null \| 4096 \| ## Benchmarks ![](https://i.ibb.co/V3rr5wM/Nous-Hermes-2-SOLAR-10-7-B-misaligned.png) # Original Model Card # About [Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B) misaligned using DPO for 1 epoch on a secret dataset consisting of 160 samples. ## Inference ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM model_id = "bn22/Nous-Hermes-2-SOLAR-10.7B-MISALIGNED" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto", load_in_4bit=True, ) prompt = "How do I get the total number of a parameters for a pytorch model?" prompt_formatted = f"""<\|im_start\|>system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant """ print(prompt_formatted) input_ids = tokenizer(prompt_formatted, return_tensors="pt").input_ids.to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ```
koesn/FuseChat-7B-VaRM-GGUF	koesn	2024-03-10T16:37:13Z	63	2	transformers	[ "transformers", "gguf", "mistral", "mixtral", "solar", "model-fusion", "fusechat", "text-generation", "en", "arxiv:2402.16107", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-03-04T01:13:31Z	--- license: apache-2.0 language: - en pipeline_tag: text-generation tags: - mistral - mixtral - solar - model-fusion - fusechat library_name: transformers --- # FuseChat-7B-VaRM ## Description This repo contains GGUF format model files for FuseChat-7B-VaRM. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ----------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| fusechat-7b-varm.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 3.02 GB \| 3.06 bpw quantization \| \| fusechat-7b-varm.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| fusechat-7b-varm.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| fusechat-7b-varm.Q4_0.gguf \| Q4_0 \| 4 \| 4.11 GB \| 3.56G, +0.2166 ppl \| \| fusechat-7b-varm.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| fusechat-7b-varm.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| fusechat-7b-varm.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| fusechat-7b-varm.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| fusechat-7b-varm.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ----------------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| FuseAI/FuseChat-7B-VaRM \| mistral \| MistralForCausalLM \| 10000.0 \| 4096 \| 8192 \| ## Benchmarks ![](https://i.ibb.co/Z2WJqbT/Fuse-Chat-7-B-Va-RM.png) ## Specific Purpose Notes This model has high MT-Bench score, comparable to GPT-3.5-Turbo. See original model card below. # Original Model Card <p align="center" width="100%"> </p> <div id="top" align="center"> <p style="font-size: 32px; font-weight: bold;">FuseChat: Knowledge Fusion of Chat Models</p> <h4> \|<a href="https://arxiv.org/abs/2402.16107"> 📑 Paper </a> \| <a href="https://huggingface.co/FuseAI"> 🤗 Huggingface Repo </a> \| <a href="https://github.com/fanqiwan/FuseLLM"> 🐱 Github Repo </a> \| </h4> <!-- Authors: --> _Fanqi Wan, Ziyi Yang, Longguang Zhong, Xiaojun Quan, Xinting Huang, Wei Bi_ <!-- Affiliations: --> _Sun Yat-sen University_ <p align="center"> <img src="./assets/fig_0.png" width="70%"> <br> </p> \| Proprietary Models \| #Params \| MT-Bench \| Open Source Models \| #Params \| MT-Bench \| \|-----------------------------------------------------------------------\|---------\|----------\|-----------------------------------------------------------------------\|---------\|----------\| \| GPT-4-1106-preview \| - \| 9.32 \| Qwen1.5-72B-Chat \| 72B \| 8.61 \| \| GPT-4-0613 \| - \| 9.18 \| Nous-Hermes-2-Mixtral-8x7B-DPO \| 8x7B \| 8.33 \| \| GPT-4-0314 \| - \| 8.96 \| Mixtral-8x7B-Instruct-v0.1 \| 8x7B \| 8.30 \| \| Mistral Medium \| - \| 8.61 \| 🤗 [FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM) \| 7B \| 8.22 \| \| GPT-3.5-Turbo-0613 \| - \| 8.39 \| Starling-LM-7B-alpha \| 7B \| 8.09 \| \| GPT-3.5-Turbo-1106 \| - \| 8.32 \| Tulu-2-DPO-70B \| 70B \| 7.89 \| \| 🤗 [FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM) \| 7B \| 8.22 \| OpenChat-3.5 \| 7B \| 7.81 \| \| Claude-2.1 \| - \| 8.18 \| OpenChat-3.5-0106 \| 7B \| 7.80 \| \| Claude-2.0 \| - \| 8.06 \| WizardLM-70B-v1.0 \| 70B \| 7.71 \| \| GPT-3.5-Turbo-0314 \| - \| 7.94 \| Yi-34B-Chat \| 34B \| 7.67 \| \| Claude-1 \| - \| 7.90 \| Nous-Hermes-2-SOLAR-10.7B \| 10.7B \| 7.66 \| </div> ## News - Feb 26, 2024: 🔥 We release [FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM), which is the fusion of three prominent chat LLMs with diverse architectures and scales, namely [NH2-Mixtral-8x7B](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO), [NH2-Solar-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B), and [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5). FuseChat-7B-VaRM achieves an average performance of 8.22 on MT-Bench, outperforming various powerful chat LLMs at 7B and 34B scales like [Starling-7B](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) and [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat), even surpassing [GPT-3.5 (March)](https://platform.openai.com/docs/models/gpt-3-5-turbo), [Claude-2.1](https://www.anthropic.com/news/claude-2-1), and approaching [Mixtral-8x7B-Instruct](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1). ## Contents - [Overview](#overview) - [Model Release](#model-release) - [Quick Start](#quick-start) - [Data Construction](#data-construction) - [Pairwise Knowledge Fusion](#pairwise-knowledge-fusion) - [Model Merging](#model-merging) - [Evaluation](#evaluation) - [Citation](#citation) ## Overview In this work, we propose an extended framework of FuseLLM to integrate the collective knowledge and individual strengths of multiple structure and scale-varied chat LLMs into a more powerful chat LLM, resulting in FuseChat. FuseChat adopts a fuse-then-merge strategy with two main stages. Firstly, it undertakes pairwise knowledge fusion for source LLMs to derive multiple target LLMs of identical structure and size via lightweight fine-tuning. Then, these target LLMs are merged within the parameter space, wherein we propose a novel method VaRM for determining the merging weights based on the variation ratio of parameter matrices before and after fine-tuning. Moreover, we argue that the concept of knowledge fusion adopted by both FuseChat and FuseLLM shares a fundamentally similar purpose with other related topics, such as the recently popular topic of mixture of experts (MoEs), because they all aim to leverage the strengths of multiple models (experts). However, while MoEs require loading multiple experts during inference, which has higher memory requirements, knowledge fusion supports the integration of multiple LLMs with diverse architectures into a single LLM without any additional memory requirement, making it more memory-efficient. <p align="center"> <img src="./assets/fig_1.png" width="95%"> <br> </p> ## Model Release We release [FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM), which is the fusion of three prominent chat LLMs with diverse architectures and scales, namely [NH2-Mixtral-8x7B](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO), [NH2-Solar-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B), and [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5). FuseChat-7B-VaRM achieves an average performance of 8.22 on MT-Bench, outperforming various powerful chat LLMs at 7B and 34B scales like [Starling-7B](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) and [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat), even surpassing [GPT-3.5 (March)](https://platform.openai.com/docs/models/gpt-3-5-turbo), [Claude-2.1](https://www.anthropic.com/news/claude-2-1), and approaching [Mixtral-8x7B-Instruct](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1). To support a plug-and-play fusion of new source LLM, we release our target LLMs: [OpenChat-3.5-7B-Solar](https://huggingface.co/FuseAI/OpenChat-3.5-7B-Solar) and [OpenChat-3.5-7B-Mixtral](https://huggingface.co/FuseAI/OpenChat-3.5-7B-Mixtral), which are obtained from pair-wise knowledge fusion. Integrating a new source LLM at any scale requires only obtaining a target LLM from the new source LLM and merging it with the existing target LLMs. We also release FuseChat with other merging methods: [FuseChat-7B-SLERP](https://huggingface.co/FuseAI/FuseChat-7B-SLERP) and [FuseChat-7B-TA](https://huggingface.co/FuseAI/FuseChat-7B-TA), which achieves an average performance of 8.19 and 8.20 on MT-Bench respectively. Here are the evaluation results. <p align="center"> <img src="./assets/tab_1.png" width="95%"> <br> </p> ## Quick Start ### Setup We use `python 3.11` in this project. Then, we have to install all the libraries listed in `requirements.txt`. ```bash pip install -r requirements.txt ``` ### Usage Here's how you can run the model using the 🤗 Transformers: ```python import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("FuseAI/FuseChat-7B-VaRM") # Single-turn tokens = tokenizer("GPT4 Correct User: Hello<\|end_of_turn\|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Multi-turn tokens = tokenizer("GPT4 Correct User: Hello<\|end_of_turn\|>GPT4 Correct Assistant: Hi<\|end_of_turn\|>GPT4 Correct User: How are you today?<\|end_of_turn\|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] ``` The GPT4 template is also available as the integrated `tokenizer.chat_template`, which can be used instead of manually specifying the template: ```python messages = [ {"role": "user", "content": "Hello"}, {"role": "assistant", "content": "Hi"}, {"role": "user", "content": "How are you today?"} ] tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True) assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] ``` ## Data Construction We curated a comprehensive training dataset, [FuseChat-Mixture](https://huggingface.co/datasets/FuseAI/FuseChat-Mixture), from various sources. This dataset covers different styles and capabilities, featuring both human-written and model-generated, and spanning general instruction-following and specific skills. Here we show the scripts to obtain representations from multiple source LLMs for model fusion. 1. Get representations for each source LLM ```bash # We split the dataset into 4 splits, then process each split on one or multiple GPU. # OpenChat-3.5-7B export CUDA_VISIBLE_DEVICES=0 for i in {0..3}; do python /train/get_data_representation.py \ --model_name_or_path "openchat/openchat_3.5" \ --data_path "/data/fusechat_v1_clean_split_2048_filter_wrong.json" \ --dataset_save_dir "<${i}_4_path_to_openchat_representation>" \ --tknz_dataset_path "<${i}_4_path_to_openchat_tknz>" \ --cache_dir "/.cache/huggingface/datasets" \ --model_max_length 2048 \ --load_in_half bf16 \ --batch_size 32 \ --top_k_logits 10 \ --save_per_token_metric \ --no_assert \ --conv_temp "openchat" \ --flash_attn_transformers \ --mask_instruction \ --dataset_split_num 4 \ --dataset_index ${i} done # NH2-Mixtral-8x7B export CUDA_VISIBLE_DEVICES=0,1,2 for i in {0..3}; do python /train/get_data_representation.py \ --model_name_or_path "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO" \ --data_path "/data/fusechat_v1_clean_split_2048_filter_wrong.json" \ --dataset_save_dir "<${i}_4_path_to_mixtral_representation>" \ --tknz_dataset_path "<${i}_4_path_to_mixtral_tknz>" \ --cache_dir "/.cache/huggingface/datasets" \ --model_max_length 2048 \ --load_in_half bf16 \ --batch_size 4 \ --top_k_logits 10 \ --save_per_token_metric \ --no_assert \ --conv_temp "openchat" \ --flash_attn_transformers \ --mask_instruction \ --device_map "auto" \ --dataset_split_num 4 \ --dataset_index ${i} done # NH2-Solar-10.7B export CUDA_VISIBLE_DEVICES=0 for i in {0..3}; do python /train/get_data_representation.py \ --model_name_or_path "NousResearch/Nous-Hermes-2-SOLAR-10.7B" \ --data_path "/data/fusechat_v1_clean_split_2048_filter_wrong.json" \ --dataset_save_dir "<${i}_4_path_to_solar_representation>" \ --tknz_dataset_path "<${i}_4_path_to_solar_tknz>" \ --cache_dir "/.cache/huggingface/datasets" \ --model_max_length 2048 \ --load_in_half bf16 \ --batch_size 8 \ --top_k_logits 10 \ --save_per_token_metric \ --no_assert \ --conv_temp "openchat" \ --flash_attn_transformers \ --mask_instruction \ --dataset_split_num 4 \ --dataset_index ${i} done ``` 2. Align representations from different source LLMs ```bash # Since the tokenizers and vocabularies of these source LLMs are identical, we do not align. # OpenChat-3.5-7B <-> NH2-Mixtral-8x7B for i in {0..3}; do python /train/replace_model.py \ --dataset_dir "<${i}_4_path_to_openchat_representation>" \ --replace_dataset_dir "<${i}_4_path_to_mixtral_representation>" \ --dataset_save_dir "<${i}_4_path_to_openchat_mixtral_representation>" \ --preprocessing_num_workers 64 \ --batch_size 1000 \ --replace_model model_0 done # OpenChat-3.5-7B <-> NH2-Solar-10.7B for i in {0..3}; do python /train/replace_model.py \ --dataset_dir "<${i}_4_path_to_openchat_mixtral_representation>" \ --replace_dataset_dir "<${i}_4_path_to_solar_representation>" \ --dataset_save_dir "<${i}_4_path_to_openchat_mixtral_solar_representation>" \ --preprocessing_num_workers 64 \ --batch_size 1000 \ --replace_model model_1 done ``` 3. Filter instances with NaN loss in the dataset ```bash for i in {0..3}; do python /train/filter_nan.py \ --input_data_dir "<${i}_4_path_to_openchat_mixtral_solar_representation>" \ --output_data_dir "<${i}_4_path_to_openchat_mixtral_solar_representation_fnan>" done ``` The final processed data is at `<${i}_4_path_to_openchat_mixtral_solar_representation_fnan>`. ## Pairwise Knowledge Fusion We show the scripts for pairwise knowledge fusion. ```bash # OpenChat-3.5-7B <-> NH2-Mixtral-8x7B export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 torchrun --nproc_per_node=8 --master_port=20001 /train/train.py \ --model_name_or_path "openchat/openchat_3.5" \ --data_path "<0_4_path_to_openchat_mixtral_solar_representation_fnan>,<1_4_path_to_openchat_mixtral_solar_representation_fnan>,<2_4_path_to_openchat_mixtral_solar_representation_fnan>,<3_4_path_to_openchat_mixtral_solar_representation_fnan>" \ --bf16 True \ --output_dir "<path_to_save_openchat_mixtral_ckpt>" \ --num_train_epochs 3 \ --per_device_train_batch_size 4 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 4 \ --evaluation_strategy "no" \ --save_strategy "epoch" \ --save_steps 10000 \ --save_total_limit 5 \ --learning_rate 5e-6 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --fsdp "full_shard auto_wrap" \ --fsdp_transformer_layer_cls_to_wrap 'MistralDecoderLayer' \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --conv_temp "openchat" \ --lazy_preprocess True \ --flash_attn_transformers True \ --do_train \ --do_distill \ --distill_with_ref_model True \ --distill_with_aligned_model_0 True \ --distill_with_aligned_model_1 False \ --distill_loss_type "ce" \ --distill_teacher_temperature 1.0 \ --lm_loss_weight 0.9 \ --distill_greater_as_gt True \ --distill_greater_as_gt_type hard \ --dataloader_num_workers 8 \ --remove_unused_columns False # OpenChat-3.5-7B <-> NH2-Solar-10.7B export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 torchrun --nproc_per_node=8 --master_port=20001 /train/train.py \ --model_name_or_path "openchat/openchat_3.5" \ --data_path "<0_4_path_to_openchat_mixtral_solar_representation_fnan>,<1_4_path_to_openchat_mixtral_solar_representation_fnan>,<2_4_path_to_openchat_mixtral_solar_representation_fnan>,<3_4_path_to_openchat_mixtral_solar_representation_fnan>" \ --bf16 True \ --output_dir "<path_to_save_openchat_solar_ckpt>" \ --num_train_epochs 3 \ --per_device_train_batch_size 4 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 4 \ --evaluation_strategy "no" \ --save_strategy "epoch" \ --save_steps 10000 \ --save_total_limit 5 \ --learning_rate 5e-6 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --fsdp "full_shard auto_wrap" \ --fsdp_transformer_layer_cls_to_wrap 'MistralDecoderLayer' \ --tf32 True \ --model_max_length 2048 \ --gradient_checkpointing True \ --conv_temp "openchat" \ --lazy_preprocess True \ --flash_attn_transformers True \ --do_train \ --do_distill \ --distill_with_ref_model True \ --distill_with_aligned_model_0 False \ --distill_with_aligned_model_1 True \ --distill_loss_type "ce" \ --distill_teacher_temperature 1.0 \ --lm_loss_weight 0.9 \ --distill_greater_as_gt True \ --distill_greater_as_gt_type hard \ --dataloader_num_workers 8 \ --remove_unused_columns False ``` ## Model Merging We show the scripts to obtain the final FuseChat using different merging methods. ```bash # For "slerp", "ta", "ties", and "dare" methods (Please install "mergekit") export CUDA_VISIBLE_DEVICES=0 mergekit-yaml merge/mergekit_configs/fusechat-slerp.yml "<path_to_save_fusechat_7b_slerp>" mergekit-yaml merge/mergekit_configs/fusechat-ta.yml "<path_to_save_fusechat_7b_ta>" mergekit-yaml merge/mergekit_configs/fusechat-ties.yml "<path_to_save_fusechat_7b_ties>" mergekit-yaml merge/mergekit_configs/fusechat-dare.yml "<path_to_save_fusechat_7b_dare>" # For "linear" method python merge/VaRM/merge.py \ --merged_model_names "FuseAI/OpenChat-3.5-7B-Mixtral,FuseAI/OpenChat-3.5-7B-Solar" \ --merged_model_save_dir "<path_to_save_fusechat_7b_linear>" \ --merge_method "linear" \ --linear_weights "1,2" # For our "varm" method python merge/VaRM/analysis.py \ --model1_path "FuseAI/OpenChat-3.5-7B-Mixtral" \ --model2_path "FuseAI/OpenChat-3.5-7B-Solar" \ --save_path "<path_to_save_analysis_result>/analysis.json" \ --merge_type "square" python merge/VaRM/merge.py \ --merged_model_names "FuseAI/OpenChat-3.5-7B-Mixtral,FuseAI/OpenChat-3.5-7B-Solar" \ --analysis_result "<path_to_save_analysis_result>/analysis.json" \ --merged_model_save_dir "<path_to_save_fusechat_7b_varm>" \ --merge_method "avg_param" \ --merge_type "square" ``` ## Evaluation We evaluate FuseChat on MT-Bench, which comprises 80 multi-turn dialogues spanning writing, roleplay, reasoning, math, coding, stem, and humanities domains. Please download the [official code](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) and follow the guidelines for evaluation. We provide the scripts for our evaluation. ```bash # Step 1. Generate model answers to MT-bench questions export CUDA_VISIBLE_DEVICES=0,1 python gen_model_answer.py \ --model-path "FuseAI/FuseChat-7B-VaRM" \ --model-id "openchat_3.5_fusechat_7b_varm" \ --num-gpus-per-model 1 \ --num-gpus-total 2 # Step 2. Generate GPT-4 judgments export OPENAI_API_KEY=XXXXXX # set the OpenAI API key python gen_judgment.py \ --parallel 2 # Step 3. Show MT-bench scores python show_result.py ``` ## Citation If you find this work is relevant with your research or applications, please feel free to cite our work! ``` @article{wan2024fusechat, title={FuseChat: Knowledge Fusion of Chat Models}, author={Fanqi Wan and Ziyi Yang and Longguang Zhong and Xiaojun Quan and Xinting Huang and Wei Bi}, journal={arXiv preprint arXiv:2402.16107}, year={2024} } ```
koesn/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF	koesn	2024-03-10T16:36:30Z	20	1	null	[ "gguf", "moe", "DPO", "RL-TUNED", "license:mit", "endpoints_compatible", "region:us" ]	null	2024-03-04T02:50:49Z	--- license: mit tags: - moe - DPO - RL-TUNED --- # Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B ## Description This repo contains GGUF format model files for Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ------------------------------------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.IQ3_XXS.gguf \| IQ3_XXS \| 3 \| 5.30 GB \| 3.06 bpw quantization \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.IQ3_S.gguf \| IQ3_S \| 3 \| 5.60 GB \| 3.44 bpw quantization \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.IQ3_M.gguf \| IQ3_M \| 3 \| 5.74 GB \| 3.66 bpw quantization mix \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.Q4_0.gguf \| Q4_0 \| 4 \| 7.28 GB \| 3.56G, +0.2166 ppl \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.IQ4_NL.gguf \| IQ4_NL \| 4 \| 7.36 GB \| 4.25 bpw non-linear quantization \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.Q4_K_M.gguf \| Q4_K_M \| 4 \| 7.78 GB \| 3.80G, +0.0532 ppl \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.Q5_K_M.gguf \| Q5_K_M \| 5 \| 9.13 GB \| 4.45G, +0.0122 ppl \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.Q6_K.gguf \| Q6_K \| 6 \| 10.57 GB \| 5.15G, +0.0008 ppl \| \| truthful_dpo_tomgrc_fusionnet_7bx2_moe_13b.Q8_0.gguf \| Q8_0 \| 8 \| 13.69 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ------------------------------------------------------ \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B \| mixtral \| MixtralForCausalLM \| 10000.0 \| null \| 32768 \| ## Benchmarks ![](https://i.ibb.co/QNW0WJr/Truthful-DPO-Tom-Grc-Fusion-Net-7-Bx2-Mo-E-13-B.png) # Original Model Card * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer) with dataset jondurbin/truthy-dpo-v0.1 to improve [TomGrc/FusionNet_7Bx2_MoE_14B] ``` DPO Trainer TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023. ```
koesn/NeuralHermes-2.5-Mistral-7B-GGUF	koesn	2024-03-10T16:34:23Z	15	0	null	[ "gguf", "mistral", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "distillation", "dpo", "rlhf", "en", "dataset:mlabonne/chatml_dpo_pairs", "base_model:teknium/OpenHermes-2.5-Mistral-7B", "base_model:quantized:teknium/OpenHermes-2.5-Mistral-7B", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us", "conversational" ]	null	2024-03-10T02:19:04Z	--- language: - en license: apache-2.0 tags: - mistral - instruct - finetune - chatml - gpt4 - synthetic data - distillation - dpo - rlhf datasets: - mlabonne/chatml_dpo_pairs base_model: teknium/OpenHermes-2.5-Mistral-7B model-index: - name: NeuralHermes-2.5-Mistral-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 66.55 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 84.9 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 63.32 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 54.93 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 78.3 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 61.33 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralHermes-2.5-Mistral-7B name: Open LLM Leaderboard --- # NeuralHermes-2.5-Mistral-7B ## Description This repo contains GGUF format model files for NeuralHermes-2.5-Mistral-7B. ## Files Provided \| Name \| Quant \| Bits \| File Size \| Remark \| \| ---------------------------- \| ------- \| ---- \| --------- \| -------------------------------- \| \| neuralhermes-2.5-mistral-7b.IQ3_S.gguf \| IQ3_S \| 3 \| 3.18 GB \| 3.44 bpw quantization \| \| neuralhermes-2.5-mistral-7b.IQ3_M.gguf \| IQ3_M \| 3 \| 3.28 GB \| 3.66 bpw quantization mix \| \| neuralhermes-2.5-mistral-7b.Q4_0.gguf \| Q4_0 \| 4 \| 4.11 GB \| 3.56G, +0.2166 ppl \| \| neuralhermes-2.5-mistral-7b.IQ4_NL.gguf \| IQ4_NL \| 4 \| 4.16 GB \| 4.25 bpw non-linear quantization \| \| neuralhermes-2.5-mistral-7b.Q4_K_M.gguf \| Q4_K_M \| 4 \| 4.37 GB \| 3.80G, +0.0532 ppl \| \| neuralhermes-2.5-mistral-7b.Q5_K_M.gguf \| Q5_K_M \| 5 \| 5.13 GB \| 4.45G, +0.0122 ppl \| \| neuralhermes-2.5-mistral-7b.Q6_K.gguf \| Q6_K \| 6 \| 5.94 GB \| 5.15G, +0.0008 ppl \| \| neuralhermes-2.5-mistral-7b.Q8_0.gguf \| Q8_0 \| 8 \| 7.70 GB \| 6.70G, +0.0004 ppl \| ## Parameters \| path \| type \| architecture \| rope_theta \| sliding_win \| max_pos_embed \| \| ---------------------------- \| ------- \| ------------------ \| ---------- \| ----------- \| ------------- \| \| teknium/OpenHermes-2.5-Mistral-7B \| mistral \| MistralForCausalLM \| 10000 \| 4096 \| 32768 \| ## Benchmarks ![](https://i.ibb.co/N2kwGJY/Neural-Hermes-2-5-Mistral-7-B.png) # Original Model Card <center><img src="https://i.imgur.com/qIhaFNM.png"></center> # NeuralHermes 2.5 - Mistral 7B NeuralHermes is based on the [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) model that has been further fine-tuned with Direct Preference Optimization (DPO) using the [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) dataset. It surpasses the original model on most benchmarks (see results). It is directly inspired by the RLHF process described by [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1)'s authors to improve performance. I used the same dataset and reformatted it to apply the ChatML template. The code to train this model is available on [Google Colab](https://colab.research.google.com/drive/15iFBr1xWgztXvhrj5I9fBv20c7CFOPBE?usp=sharing) and [GitHub](https://github.com/mlabonne/llm-course/tree/main). It required an A100 GPU for about an hour. ## Quantized models * GGUF: https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-GGUF * AWQ: https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-AWQ * GPTQ: https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-GPTQ * EXL2: * 3.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-3.0bpw-h6-exl2 * 4.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-4.0bpw-h6-exl2 * 5.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-5.0bpw-h6-exl2 * 6.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-6.0bpw-h6-exl2 * 8.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2 ## Results Update: NeuralHermes-2.5 became the best Hermes-based model on the Open LLM leaderboard and one of the very best 7b models. 🎉 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/yWe6VBFxkHiuOlDVBXtGo.png) Teknium (author of OpenHermes-2.5-Mistral-7B) benchmarked the model ([see his tweet](https://twitter.com/Teknium1/status/1729955709377503660)). Results are improved on every benchmark: AGIEval (from 43.07% to 43.62%), GPT4All (from 73.12% to 73.25%), and TruthfulQA. ### AGIEval ![](https://i.imgur.com/7an3B1f.png) ### GPT4All ![](https://i.imgur.com/TLxZFi9.png) ### TruthfulQA ![](https://i.imgur.com/V380MqD.png) You can check the Weights & Biases project [here](https://wandb.ai/mlabonne/NeuralHermes-2-5-Mistral-7B/overview?workspace=user-mlabonne). ## Usage You can run this model using [LM Studio](https://lmstudio.ai/) or any other frontend. You can also run this model using the following code: ```python import transformers from transformers import AutoTokenizer # Format prompt message = [ {"role": "system", "content": "You are a helpful assistant chatbot."}, {"role": "user", "content": "What is a Large Language Model?"} ] tokenizer = AutoTokenizer.from_pretrained(new_model) prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False) # Create pipeline pipeline = transformers.pipeline( "text-generation", model=new_model, tokenizer=tokenizer ) # Generate text sequences = pipeline( prompt, do_sample=True, temperature=0.7, top_p=0.9, num_return_sequences=1, max_length=200, ) print(sequences[0]['generated_text']) ``` ## Training hyperparameters LoRA: * r=16 * lora_alpha=16 * lora_dropout=0.05 * bias="none" * task_type="CAUSAL_LM" * target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj'] Training arguments: * per_device_train_batch_size=4 * gradient_accumulation_steps=4 * gradient_checkpointing=True * learning_rate=5e-5 * lr_scheduler_type="cosine" * max_steps=200 * optim="paged_adamw_32bit" * warmup_steps=100 DPOTrainer: * beta=0.1 * max_prompt_length=1024 * max_length=1536
casque/hip_covering_skirt	casque	2024-03-10T16:34:23Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2024-03-10T16:30:30Z	--- license: creativeml-openrail-m ---
femboysLover/anything-XL	femboysLover	2024-03-10T16:33:40Z	30	0	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2024-03-10T16:30:41Z	--- library_name: diffusers --- # 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 🧨 diffusers 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]
lilyray/distilbert	lilyray	2024-03-10T16:27:44Z	5	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T15:58:51Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: distilbert results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6232 - Accuracy: 0.6467 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 4.268152647097221e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 2 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 179 \| 0.5912 \| 0.6701 \| \| No log \| 2.0 \| 358 \| 0.6109 \| 0.6837 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
hamzasidat/Hamzas_Emotional_Albert	hamzasidat	2024-03-10T16:15:21Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T16:15:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
hamzasidat/AlbertEmotionResults	hamzasidat	2024-03-10T16:15:19Z	177	0	transformers	[ "transformers", "tensorboard", "safetensors", "albert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:albert/albert-base-v2", "base_model:finetune:albert/albert-base-v2", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T16:15:14Z	--- license: apache-2.0 base_model: albert-base-v2 tags: - generated_from_trainer datasets: - emotion metrics: - accuracy model-index: - name: AlbertEmotionResults results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion config: split split: validation args: split metrics: - name: Accuracy type: accuracy value: 0.936 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # AlbertEmotionResults This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.1459 - Accuracy: 0.936 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.2616 \| 1.0 \| 1000 \| 0.2192 \| 0.917 \| \| 0.1326 \| 2.0 \| 2000 \| 0.1459 \| 0.936 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
imgmongelli/modelassistant	imgmongelli	2024-03-10T16:12:10Z	0	0	null	[ "safetensors", "text-generation", "fine-tuning", "conversational", "license:other", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T15:51:52Z	--- tags: - text-generation - fine-tuning widget: - text: 'Fine-tuning ' license: other --- # Model Trained Using AutoTrain This model was trained by mac. # Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) ```
ed-butcher/ppo-LunarLander-v2	ed-butcher	2024-03-10T16:11:21Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-03-10T15:03:37Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: -655.80 +/- 106.53 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
abideen/MonarchCoder-MoE-2x7B	abideen	2024-03-10T16:11:15Z	52	1	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "mlabonne/AlphaMonarch-7B", "Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0", "en", "base_model:Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0", "base_model:merge:Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0", "base_model:mlabonne/AlphaMonarch-7B", "base_model:merge:mlabonne/AlphaMonarch-7B", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-19T16:35:35Z	--- license: apache-2.0 tags: - moe - frankenmoe - merge - mergekit - lazymergekit - mlabonne/AlphaMonarch-7B - Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0 base_model: - mlabonne/AlphaMonarch-7B - Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0 language: - en library_name: transformers model-index: - name: MonarchCoder-MoE-2x7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 70.99 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 87.99 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 65.11 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 71.25 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 80.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 69.37 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B name: Open LLM Leaderboard --- # MonarchCoder-MoE-2x7B ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/eoHRSEuT-_TtlrPX7PrOW.jpeg) MonarchCoder-MoE-2x7B is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) * [Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0](https://huggingface.co/Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0) The main aim behind creating this model is to create a model that performs well in reasoning, conversation, and coding. AlphaMonarch performs amazing on reasoning and conversation tasks. Merging AlphaMonarch with a coding model yielded MonarchCoder-2x7B which performs better on OpenLLM, Nous, and HumanEval benchmark. ## 🏆 Evaluation results ``` \| Metric \|MonarchCoder-Moe-2x7B\|\|MonarchCoder-7B\|\|AlphaMonarch\| \|---------------------------------\|---------------------\|-----------------\|------------\| \|Avg. \| 74.23 \| 71.17 \| 75.99 \| \|HumanEval \| 41.15 \| 39.02 \| 34.14 \| \|HumanEval+ \| 29.87 \| 31.70 \| 29.26 \| \|MBPP \| 40.60 \| * \| * \| \|AI2 Reasoning Challenge (25-Shot)\| 70.99 \| 68.52 \| 73.04 \| \|HellaSwag (10-Shot) \| 87.99 \| 87.30 \| 89.18 \| \|MMLU (5-Shot) \| 65.11 \| 64.65 \| 64.40 \| \|TruthfulQA (0-shot) \| 71.25 \| 61.21 \| 77.91 \| \|Winogrande (5-shot) \| 80.66 \| 80.19 .\| 84.69 \| \|GSM8k (5-shot) . \| 69.37 \| 65.13 \| 66.72 \| ``` ## 🧩 Configuration ```yaml base_model: paulml/OGNO-7B gate_mode: hidden dtype: bfloat16 experts: - source_model: mlabonne/AlphaMonarch-7B positive_prompts: - "Mathematics" - "Logical Reasoning" - "Intelligent Conversations" - "Thoughtful Analysis" - "Biology" - "Medicine" - "Problem-solving Dialogue" - "Physics" - "Emotional intelligence" negative_prompts: - "History" - "Philosophy" - "Linguistics" - "Literature" - "Art and Art History" - "Music Theory and Composition" - "Performing Arts (Theater, Dance)" - source_model: Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0 positive_prompts: - "Coding" - "Algorithm Design" - "Problem Solving" - "Software Development" - "Computer" - "Code Refactoring" - "Web development" - "Machine learning" negative_prompts: - "Education" - "Law" - "Theology and Religious Studies" - "Communication Studies" - "Business and Management" - "Agricultural Sciences" - "Nutrition and Food Science" - "Sports Science" ``` ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "abideen/MonarchCoder-MoE-2x7B" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
hamzasidat/Hamzas_Emotional_Berty	hamzasidat	2024-03-10T16:02:20Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T16:02:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
hamzasidat/BertEmotionResults	hamzasidat	2024-03-10T16:02:19Z	178	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T16:02:00Z	--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer datasets: - emotion metrics: - accuracy model-index: - name: BertEmotionResults results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion config: split split: validation args: split metrics: - name: Accuracy type: accuracy value: 0.94 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # BertEmotionResults This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.1391 - Accuracy: 0.94 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.2171 \| 1.0 \| 1000 \| 0.1834 \| 0.932 \| \| 0.1163 \| 2.0 \| 2000 \| 0.1391 \| 0.94 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
asigalov61/Tiny-Music-Transformer	asigalov61	2024-03-10T16:00:38Z	0	1	null	[ "license:apache-2.0", "region:us" ]	null	2023-12-14T05:11:11Z	--- license: apache-2.0 --- # Tiny Music Transformer ## Miniature multi-instrumental music transformer with super-efficient encoding ![Tiny-Music-Transformer-Artwork (2)](https://github.com/asigalov61/Tiny-Music-Transformer/assets/56325539/6798f560-6b93-4afb-982a-5b34e100625e) * ## [NEW] Enhanced Version [![Open In Colab][colab-badge]][colab-notebook2] [colab-notebook2]: <https://colab.research.google.com/github/asigalov61/Tiny-Music-Transformer/blob/main/Enhanced_Tiny_Music_Transformer.ipynb> [colab-badge]: <https://colab.research.google.com/assets/colab-badge.svg> ### Features demonstration * ## [DEPRECIATED] Original Version [![Open In Colab][colab-badge]][colab-notebook1] [colab-notebook1]: <https://colab.research.google.com/github/asigalov61/Tiny-Music-Transformer/blob/main/Tiny_Music_Transformer.ipynb> [colab-badge]: <https://colab.research.google.com/assets/colab-badge.svg> ### Features demonstration *** ### Project Los Angeles ### Tegridy Code 2024
AlexWortega/tini_llama_freeze	AlexWortega	2024-03-10T16:00:27Z	0	0	transformers	[ "transformers", "dataset:dichspace/darulm", "endpoints_compatible", "region:us" ]	null	2024-02-08T11:52:26Z	--- library_name: transformers datasets: - dichspace/darulm ---
nold/SauerkrautLM-Gemma-7b-GGUF	nold	2024-03-10T15:55:32Z	28	0	null	[ "gguf", "sft", "dpo", "laserRMT", "laser-QLoRa", "finetune", "work in progress", "alpha", "de", "en", "license:other", "endpoints_compatible", "region:us" ]	null	2024-03-10T11:55:04Z	--- license: other license_name: gemma-terms-of-use license_link: https://ai.google.dev/gemma/terms language: - de - en tags: - sft - dpo - laserRMT - laser-QLoRa - finetune - work in progress - alpha --- Update - 01.03.2024 - Reuploaded the model in bfloat16 dtype. - 02.03.2024 - strongest Gemma finetune model so far: added AGIEval,GPT4ALL and Bigbench scoring with AVG of 54.13 and H6 Open LLM Leaderboard with AVG of 67.83 ![SauerkrautLM](https://vago-solutions.de/wp-content/uploads/2024/02/sauerkrautgemma.jpeg "SauerkrautLM-Gemma-7b") ## VAGO solutions SauerkrautLM-Gemma-7b (alpha) Introducing SauerkrautLM-Gemma-7b – our Sauerkraut version of the powerful [google/gemma-7b](https://huggingface.co/google/gemma-7b) ! It is an early stage finetuned model and should be used with caution! The model SauerkrautLM-Gemma-7b is a joint effort between VAGO solutions and Hyperspace.ai. Much appreciation goes to the tremendous research effort of Fernando Fernandes Neto, David Golchinfar and Eric Hartford on their laserRMT approach. Without their independent research collaboration this model release would not have been possible. - Fintuned with SFT - Aligned with DPO - Using a novel training technique: laser-QLoRA - we partially freeze the model according to a laser-like analysis (Official Paper soon). It allows to evaluate the no free lunch theorem and supports better decision making when optimizing the theorem - created by the [LaserRMT research group](https://github.com/cognitivecomputations/laserRMT) - Optimized with LaserRMT # Table of Contents 1. [Overview of all SauerkrautLM-Gemma-7b models](#all-sauerkrautlm-gemma-7b-models) 2. [Model Details](#model-details) - [Prompt template](#prompt-template) - [Training procedure](#proceed-of-the-training) 3. [Evaluation](#evaluation) 5. [Disclaimer](#disclaimer) 6. [Contact](#contact) 7. [Collaborations](#collaborations) 8. [Acknowledgement](#acknowledgement) ## All SauerkrautLM-Gemma-7b Models \| Model \| HF \| GPTQ \| GGUF \| AWQ \| \|-------\|-------\|-------\|-------\|-------\| \| SauerkrautLM-Gemma-7b \| [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b) \| coming soon \| coming soon \| coming soon \| ## Model Details SauerkrautLM-Gemma-7b - Model Type: SauerkrautLM-Gemma-7b is a finetuned Model based on [google/gemma-7b](https://huggingface.co/google/gemma-7b) - Language(s): German, English - License: [gemma-terms-of-use](https://ai.google.dev/gemma/terms) - Contact: [VAGO solutions](https://vago-solutions.ai), [Hyperspace.ai](https://hyperspace.computer/) ### Training procedure: Warning: This finetuned model is in an early stage and we sometimes observed strange behavior. It is still work in progress! Anyone who has attempted or succeeded in fine-tuning a model is aware of the difficulty in nudging it towards a specific skill, such as mastering new languages, as well as the challenges associated with achieving significant improvements in performance. Experimenting with a novel training strategy and Spherical Linear Interpolation alongside a lasered version of the model itself has proven to be both fascinating and revealing. Furthermore, we developed one iteration of the model using our entire SFT -Sauerkraut dataset and two additional iterations using subsets of the full dataset—one focused on enhancing MMLU and TQA capabilities, and the other on boosting GSM8K and Winogrande skills. After optimizing our primary SFT model, we applied a similar strategy to our new DPO Dataset, dividing it into further subsets. We trained one model on the entire dataset again and two more on these specialized subsets. We actively monitor and assesed the results of each training. Whenever we found a decrease in perplexity on the gsm8k benchmark we intervined. By following this procedure we were able to improve the overall performance, especially in math abilities, without detracting from performance on other benchmarks—a task that is, in general, quite difficult. This process not only helps in understanding the effectiveness of Spherical Linear Interpolation but also introduces a new method for refining models with enhanced skills through a cycle of targeted data selection (Laser data(x)) + SLERP, followed by a subsequent focus on different data (Laser again on data(y)). Additionally, we integrated a novel training strategy on the SFT and DPO training process, where we partially freeze the model according to a laser-like analysis aiming to navigate and optimize the trade-offs highlighted by the no free lunch theorem. This innovative training method effectively prevents the significant problem of language models forgetting previously acquired knowledge. This aspect is particularly crucial when attempting to teach the model specific skills, such as a new language, where in general, the model might lose a considerable amount of its prior knowledge and exhibit a decline in overall intelligence. Detailed information on how the new training strategy works and the advantages it offers over conventional training methods will soon be published in a detailed paper by the LaserRMT research group. We teached German language skills on this model. As far as we know, it is the first Gemma model with bilingual skills in German and English. Nevertheless, formulations may occur that are not entirely correct (still work in progress). ### Prompt Template: We trained on vicuna prompt template. Please add the following stopping string to your client: ``` "</s>","</p>" ``` (we did not add the special tokens to the training config) ``` You are a helpful AI Assistant. USER: Hello, how are you? ASSISTANT: ``` ## Evaluation Open LLM Leaderboard: \| Metric \| Value \| \|-----------------------\|---------------------------\| \| Avg. \| 67.83 \| \| ARC (25-shot) \| 59.98 \| \| HellaSwag (10-shot) \| 81.91 \| \| MMLU (5-shot) \| 63.76\| \| TruthfulQA (0-shot) \| 61 \| \| Winogrande (5-shot) \| 76.64 \| \| GSM8K (5-shot) \| 63.68 \| Performance \| Model \|AGIEval\|GPT4All\|TruthfulQA\|BigBench\|Average ⬇️\| \|-----------------------------------------------------------------------\|------:\|------:\|---------:\|-------:\|------:\| \|[VAGOsolutions/SauerkrautLM-Gemma-7b](https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b) \| 37.5\| 72.46\| 61.24\| 45.33\| 54.13\| \|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) \| 37.52\| 71.77\| 55.26\| 39.77\| 51.08\| \|[zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)\| 34.22\| 66.37\| 52.19\| 37.10\| 47.47\| \|[google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) \| 21.33\| 40.84\| 41.70\| 30.25\| 33.53\| <details><summary>Details of AGIEval, GPT4All, TruthfulQA, BigBench </summary> AGIEval \| Tasks \|Version\|Filter\|n-shot\| Metric \|Value \| \|Stderr\| \|------------------------------\|------:\|------\|------\|--------\|-----:\|---\|-----:\| \|agieval_sat_math \| 1\|none \|None \|acc \|0.3682\|± \|0.0326\| \| \| \|none \|None \|acc_norm\|0.3364\|± \|0.0319\| \|agieval_sat_en_without_passage\| 1\|none \|None \|acc \|0.4272\|± \|0.0345\| \| \| \|none \|None \|acc_norm\|0.3738\|± \|0.0338\| \|agieval_sat_en \| 1\|none \|None \|acc \|0.7427\|± \|0.0305\| \| \| \|none \|None \|acc_norm\|0.6893\|± \|0.0323\| \|agieval_lsat_rc \| 1\|none \|None \|acc \|0.5539\|± \|0.0304\| \| \| \|none \|None \|acc_norm\|0.5167\|± \|0.0305\| \|agieval_lsat_lr \| 1\|none \|None \|acc \|0.3431\|± \|0.0210\| \| \| \|none \|None \|acc_norm\|0.3471\|± \|0.0211\| \|agieval_lsat_ar \| 1\|none \|None \|acc \|0.1913\|± \|0.0260\| \| \| \|none \|None \|acc_norm\|0.1739\|± \|0.0250\| \|agieval_logiqa_en \| 1\|none \|None \|acc \|0.3303\|± \|0.0184\| \| \| \|none \|None \|acc_norm\|0.3303\|± \|0.0184\| \|agieval_aqua_rat \| 1\|none \|None \|acc \|0.2480\|± \|0.0272\| \| \| \|none \|None \|acc_norm\|0.2323\|± \|0.0265\| Average: 37.5% GPT4All \| Tasks \|Version\|Filter\|n-shot\| Metric \|Value \| \|Stderr\| \|---------\|------:\|------\|------\|--------\|-----:\|---\|-----:\| \|arc_challenge\| 1\|none \|None \|acc \|0.5358\|± \|0.0146\| \| \| \|none \|None \|acc_norm\|0.5597\|± \|0.0145\| \|arc_easy \| 1\|none \|None \|acc \|0.8249\|± \|0.0078\| \| \| \|none \|None \|acc_norm\|0.7955\|± \|0.0083\| \|boolq \| 2\|none \|None \|acc \|0.8651\|± \|0.006 \| \|hellaswag \| 1\|none \|None \|acc \|0.6162\|± \|0.0049\| \| \| \|none \|None \|acc_norm\|0.8117\|± \|0.0039\| \|openbookqa \| 1\|none \|None \|acc \|0.336\|± \|0.0211\| \| \| \|none \|None \|acc_norm\|0.470\|± \|0.0223\| \|piqa \| 1\|none \|None \|acc \|0.7900\|± \|0.0095\| \| \| \|none \|None \|acc_norm\|0.8096\|± \|0.00 \| \|winogrande \| 1\|none \|None \|acc \|0.7609\|± \|0.012 \| Average: 72.46% TruthfulQA \| Tasks \|Version\|Filter\|n-shot\|Metric\|Value \| \|Stderr\| \|--------------\|------:\|------\|-----:\|------\|-----:\|---\|-----:\| \|truthfulqa_mc2\| 2\|none \| 0\|acc \|0.6124\|± \|0.0148\| Average: 61.24% Bigbench \| Tasks \|Version\| Filter \|n-shot\| Metric \|Value \| \|Stderr\| \|----------------------------------------------------\|------:\|----------------\|-----:\|-----------\|-----:\|---\|-----:\| \|bbh_zeroshot_tracking_shuffled_objects_three_objects\| 2\|flexible-extract\| 0\|exact_match\|0.2760\|± \|0.0283\| \|bbh_zeroshot_tracking_shuffled_objects_seven_objects\| 2\|flexible-extract\| 0\|exact_match\|0.1280\|± \|0.0212\| \|bbh_zeroshot_tracking_shuffled_objects_five_objects \| 2\|flexible-extract\| 0\|exact_match\|0.1240\|± \|0.0209\| \|bbh_zeroshot_temporal_sequences \| 2\|flexible-extract\| 0\|exact_match\|0.4520\|± \|0.0315\| \|bbh_zeroshot_sports_understanding \| 2\|flexible-extract\| 0\|exact_match\|0.7120\|± \|0.0287\| \|bbh_zeroshot_snarks \| 2\|flexible-extract\| 0\|exact_match\|0.5056\|± \|0.0376\| \|bbh_zeroshot_salient_translation_error_detection \| 2\|flexible-extract\| 0\|exact_match\|0.4480\|± \|0.0315\| \|bbh_zeroshot_ruin_names \| 2\|flexible-extract\| 0\|exact_match\|0.4520\|± \|0.0315\| \|bbh_zeroshot_reasoning_about_colored_objects \| 2\|flexible-extract\| 0\|exact_match\|0.4800\|± \|0.0317\| \|bbh_zeroshot_navigate \| 2\|flexible-extract\| 0\|exact_match\|0.5480\|± \|0.0315\| \|bbh_zeroshot_movie_recommendation \| 2\|flexible-extract\| 0\|exact_match\|0.7000\|± \|0.0290\| \|bbh_zeroshot_logical_deduction_three_objects \| 2\|flexible-extract\| 0\|exact_match\|0.5200\|± \|0.0317\| \|bbh_zeroshot_logical_deduction_seven_objects \| 2\|flexible-extract\| 0\|exact_match\|0.4120\|± \|0.0312\| \|bbh_zeroshot_logical_deduction_five_objects \| 2\|flexible-extract\| 0\|exact_match\|0.3840\|± \|0.0308\| \|bbh_zeroshot_geometric_shapes \| 2\|flexible-extract\| 0\|exact_match\|0.2920\|± \|0.0288\| \|bbh_zeroshot_disambiguation_qa \| 2\|flexible-extract\| 0\|exact_match\|0.6480\|± \|0.0303\| \|bbh_zeroshot_date_understanding \| 2\|flexible-extract\| 0\|exact_match\|0.5000\|± \|0.0317\| \|bbh_zeroshot_causal_judgement \| 2\|flexible-extract\| 0\|exact_match\|0.5775\|± \|0.0362\| Average: 45.33% </details> Despite the fact that we archived great results on the Open LLM leaderboard benchmarks the model subjectively does not feel as smart as comparable mistral finetunes. Most of its answers are coherent but we observed that the model sometimes answers realy lazy or odd. ## Disclaimer We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out. However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided. Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. ## Contact If you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions. ## Collaborations We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at [VAGO solutions](https://vago-solutions.de/#Kontakt), [Hyperspace.computer](https://hyperspace.computer/) ## Acknowledgement Many thanks to [google](https://huggingface.co/google) for providing such valuable model to the Open-Source community *** Quantization of Model [VAGOsolutions/SauerkrautLM-Gemma-7b](https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b). Created using [llm-quantizer](https://github.com/Nold360/llm-quantizer) Pipeline
afaji/fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-8	afaji	2024-03-10T15:55:01Z	87	0	transformers	[ "transformers", "pytorch", "bert", "multiple-choice", "generated_from_trainer", "endpoints_compatible", "region:us" ]	multiple-choice	2024-03-10T15:54:29Z	--- tags: - generated_from_trainer metrics: - accuracy model-index: - name: fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-8 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-8 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7254 - Accuracy: 0.4747 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 16 - eval_batch_size: 16 - seed: 321 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 63 \| 3.7644 \| 0.2323 \| \| No log \| 2.0 \| 126 \| 3.6149 \| 0.3687 \| \| No log \| 3.0 \| 189 \| 1.4060 \| 0.4141 \| \| No log \| 4.0 \| 252 \| 1.4429 \| 0.4646 \| \| No log \| 5.0 \| 315 \| 1.2004 \| 0.4545 \| \| No log \| 6.0 \| 378 \| 1.0944 \| 0.4596 \| \| No log \| 7.0 \| 441 \| 1.3715 \| 0.4394 \| \| 2.4812 \| 8.0 \| 504 \| 1.1383 \| 0.4697 \| \| 2.4812 \| 9.0 \| 567 \| 1.1514 \| 0.4444 \| \| 2.4812 \| 10.0 \| 630 \| 1.4900 \| 0.4242 \| \| 2.4812 \| 11.0 \| 693 \| 0.7765 \| 0.4545 \| \| 2.4812 \| 12.0 \| 756 \| 0.7740 \| 0.4343 \| \| 2.4812 \| 13.0 \| 819 \| 1.3336 \| 0.4394 \| \| 2.4812 \| 14.0 \| 882 \| 0.7081 \| 0.4394 \| \| 2.4812 \| 15.0 \| 945 \| 0.5895 \| 0.4242 \| \| 0.2763 \| 16.0 \| 1008 \| 0.7254 \| 0.4747 \| \| 0.2763 \| 17.0 \| 1071 \| 0.6059 \| 0.4141 \| \| 0.2763 \| 18.0 \| 1134 \| 0.5857 \| 0.4495 \| \| 0.2763 \| 19.0 \| 1197 \| 0.6002 \| 0.4394 \| \| 0.2763 \| 20.0 \| 1260 \| 0.6015 \| 0.4495 \| ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0
satyroffrost/FT_Merged_TinyLlama-1.1B-Chat-v1.0	satyroffrost	2024-03-10T15:51:21Z	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-09T20:32:17Z	--- 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]
Pyjama12/q-Taxi-v3	Pyjama12	2024-03-10T15:44:15Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2024-03-10T15:44:11Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.50 +/- 2.72 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="Pyjama12/q-Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
OwOOwO/eacc_contTrain_6_2_4	OwOOwO	2024-03-10T15:37:41Z	91	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T15:35:15Z	--- 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]
PraneetNeuro/ImageNet-Small-Attention-and-MLP-Patch32	PraneetNeuro	2024-03-10T15:34:57Z	0	0	null	[ "image-classification", "dataset:imagenet-1k", "region:us" ]	image-classification	2024-03-04T21:58:32Z	--- datasets: - imagenet-1k pipeline_tag: image-classification --- ## Model Architecture Details ### Architecture Overview - Architecture: ViT Small ### Configuration \| Attribute \| Value \| \|----------------------\|----------------\| \| Patch Size \| 32 \| \| Image Size \| 224 \| \| Num Layers \| 3 \| \| Attention Heads \| 4 \| \| Objective Function \| CrossEntropy \| ### Performance - Validation Accuracy (Top 5): 0.4179 - Validation Accuracy: 0.2148 ### Additional Resources The model was trained using the library: [ViT-Prisma](https://github.com/soniajoseph/ViT-Prisma).\ For detailed metrics, plots, and further analysis of the model's training process, refer to the [training report](https://wandb.ai/perceptual-alignment/Imagenet/reports/ViT-Small-Imagenet-training-report--Vmlldzo3MDk3MTM5).
Anu2004/idefics-mscoco-captioner	Anu2004	2024-03-10T15:32:00Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T15:31:57Z	--- 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]
HachiML/myBit-Llama2-jp-127M-test-9	HachiML	2024-03-10T15:31:38Z	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "base_model:finetune:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T15:04:53Z	--- license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags: - generated_from_trainer model-index: - name: myBit-Llama2-jp-127M-test-9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # myBit-Llama2-jp-127M-test-9 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 5.7432 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0024 - train_batch_size: 96 - eval_batch_size: 96 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: polynomial - lr_scheduler_warmup_steps: 250 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 8.0298 \| 0.04 \| 100 \| 6.8090 \| \| 6.6646 \| 0.07 \| 200 \| 6.4142 \| \| 6.6122 \| 0.11 \| 300 \| 6.5336 \| \| 6.3178 \| 0.15 \| 400 \| 6.1932 \| \| 6.2234 \| 0.18 \| 500 \| 6.2133 \| \| 6.3775 \| 0.22 \| 600 \| 6.4767 \| \| 6.5634 \| 0.26 \| 700 \| 6.2278 \| \| 6.2821 \| 0.29 \| 800 \| 6.2418 \| \| 6.2629 \| 0.33 \| 900 \| 6.1478 \| \| 6.1722 \| 0.37 \| 1000 \| 6.1330 \| \| 6.1431 \| 0.4 \| 1100 \| 6.0922 \| \| 6.1409 \| 0.44 \| 1200 \| 6.0402 \| \| 6.1356 \| 0.48 \| 1300 \| 6.0740 \| \| 6.0952 \| 0.51 \| 1400 \| 6.0125 \| \| 6.0549 \| 0.55 \| 1500 \| 5.9976 \| \| 6.1898 \| 0.59 \| 1600 \| 6.0319 \| \| 6.0732 \| 0.62 \| 1700 \| 5.9750 \| \| 6.0315 \| 0.66 \| 1800 \| 5.9562 \| \| 6.016 \| 0.7 \| 1900 \| 5.9223 \| \| 5.9743 \| 0.74 \| 2000 \| 5.8803 \| \| 5.9404 \| 0.77 \| 2100 \| 6.0148 \| \| 5.9275 \| 0.81 \| 2200 \| 5.8391 \| \| 5.8828 \| 0.85 \| 2300 \| 5.8070 \| \| 5.872 \| 0.88 \| 2400 \| 5.7854 \| \| 5.8438 \| 0.92 \| 2500 \| 5.7637 \| \| 5.8367 \| 0.96 \| 2600 \| 5.7564 \| \| 5.8266 \| 0.99 \| 2700 \| 5.7432 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
abideen/Liberated-Miqu-70B	abideen	2024-03-10T15:29:14Z	3	4	transformers	[ "transformers", "pytorch", "llama", "text-generation", "Miqu", "Liberated", "Uncensored", "70B", "conversational", "en", "dataset:abacusai/SystemChat", "base_model:152334H/miqu-1-70b-sf", "base_model:finetune:152334H/miqu-1-70b-sf", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T11:41:01Z	--- license: apache-2.0 base_model: 152334H/miqu-1-70b-sf language: - en library_name: transformers tags: - Miqu - Liberated - Uncensored - 70B datasets: - abacusai/SystemChat --- # Liberated Miqu 70B ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/mxX4M4ePQJI7W4y1hdBfE.jpeg) Liberated Miqu 70B is a fine-tune of Miqu-70B on Abacus AI's SystemChat dataset. This model has been trained on 2xA100 GPUs for 1 epoch. ## 🏆 Evaluation results Coming soon ### Framework versions - Transformers 4.38.0.dev0 - Pytorch 2.1.2+cu118 - Datasets 2.17.0 - Tokenizers 0.15.0 - axolotl: 0.4.0 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
Holarissun/gpt2full-airl_sft-imdb-seqsampler	Holarissun	2024-03-10T15:22:09Z	93	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "trl", "sft", "generated_from_trainer", "base_model:openai-community/gpt2", "base_model:finetune:openai-community/gpt2", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T15:21:51Z	--- license: mit base_model: gpt2 tags: - trl - sft - generated_from_trainer model-index: - name: gpt2full-airl_sft-imdb-seqsampler results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2full-airl_sft-imdb-seqsampler This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Sayyor/q-Taxi-v3-eval-seed	Sayyor	2024-03-10T15:16:31Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2024-03-10T15:16:26Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-Taxi-v3-eval-seed results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.26 +/- 2.59 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="Sayyor/q-Taxi-v3-eval-seed", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
ThuyNT03/CS505-Classifier-T4_predictLabel_a1_v5	ThuyNT03	2024-03-10T15:15:03Z	6	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/phobert-base-v2", "base_model:finetune:vinai/phobert-base-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T14:54:59Z	--- base_model: vinai/phobert-base-v2 tags: - generated_from_trainer model-index: - name: CS505-Classifier-T4_predictLabel_a1_v5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505-Classifier-T4_predictLabel_a1_v5 This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0018 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 40 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 0.98 \| 48 \| 0.6517 \| \| No log \| 1.96 \| 96 \| 0.3227 \| \| No log \| 2.94 \| 144 \| 0.2342 \| \| No log \| 3.92 \| 192 \| 0.1815 \| \| No log \| 4.9 \| 240 \| 0.1703 \| \| No log \| 5.88 \| 288 \| 0.1231 \| \| No log \| 6.86 \| 336 \| 0.0730 \| \| No log \| 7.84 \| 384 \| 0.0803 \| \| No log \| 8.82 \| 432 \| 0.0476 \| \| No log \| 9.8 \| 480 \| 0.0384 \| \| 0.2908 \| 10.78 \| 528 \| 0.0281 \| \| 0.2908 \| 11.76 \| 576 \| 0.0329 \| \| 0.2908 \| 12.73 \| 624 \| 0.0234 \| \| 0.2908 \| 13.71 \| 672 \| 0.0119 \| \| 0.2908 \| 14.69 \| 720 \| 0.0101 \| \| 0.2908 \| 15.67 \| 768 \| 0.0081 \| \| 0.2908 \| 16.65 \| 816 \| 0.0137 \| \| 0.2908 \| 17.63 \| 864 \| 0.0075 \| \| 0.2908 \| 18.61 \| 912 \| 0.0053 \| \| 0.2908 \| 19.59 \| 960 \| 0.0035 \| \| 0.0216 \| 20.57 \| 1008 \| 0.0060 \| \| 0.0216 \| 21.55 \| 1056 \| 0.0028 \| \| 0.0216 \| 22.53 \| 1104 \| 0.0027 \| \| 0.0216 \| 23.51 \| 1152 \| 0.0026 \| \| 0.0216 \| 24.49 \| 1200 \| 0.0024 \| \| 0.0216 \| 25.47 \| 1248 \| 0.0023 \| \| 0.0216 \| 26.45 \| 1296 \| 0.0022 \| \| 0.0216 \| 27.43 \| 1344 \| 0.0022 \| \| 0.0216 \| 28.41 \| 1392 \| 0.0021 \| \| 0.0216 \| 29.39 \| 1440 \| 0.0020 \| \| 0.0216 \| 30.37 \| 1488 \| 0.0021 \| \| 0.0043 \| 31.35 \| 1536 \| 0.0020 \| \| 0.0043 \| 32.33 \| 1584 \| 0.0019 \| \| 0.0043 \| 33.31 \| 1632 \| 0.0019 \| \| 0.0043 \| 34.29 \| 1680 \| 0.0019 \| \| 0.0043 \| 35.27 \| 1728 \| 0.0019 \| \| 0.0043 \| 36.24 \| 1776 \| 0.0019 \| \| 0.0043 \| 37.22 \| 1824 \| 0.0019 \| \| 0.0043 \| 38.2 \| 1872 \| 0.0018 \| \| 0.0043 \| 39.18 \| 1920 \| 0.0018 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Omar23moh/UNIT1	Omar23moh	2024-03-10T15:14:55Z	0	1	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-03-10T02:38:04Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 260.97 +/- 12.92 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
SAGAR4REAL/q_q	SAGAR4REAL	2024-03-10T15:10:31Z	2	0	transformers	[ "transformers", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-03-02T16:48:11Z	--- 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]
alex-atelo/bert-base-uncased-sst2	alex-atelo	2024-03-10T15:06:47Z	93	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T14:56:02Z	--- 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]
xXiaobuding/deberta-v3-base_ai4privacy_en	xXiaobuding	2024-03-10T15:03:31Z	93	1	transformers	[ "transformers", "pytorch", "deberta-v2", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-03-10T02:46:05Z	--- license: mit tags: - generated_from_trainer model-index: - name: deberta-v3-base_ai4privacy_en results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # deberta-v3-base_ai4privacy_en This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1055 - Overall Precision: 0.8683 - Overall Recall: 0.8949 - Overall F1: 0.8814 - Overall Accuracy: 0.9609 - Accountname F1: 0.9898 - Accountnumber F1: 0.9939 - Age F1: 0.8397 - Amount F1: 0.9169 - Bic F1: 0.9012 - Bitcoinaddress F1: 0.9583 - Buildingnumber F1: 0.8109 - City F1: 0.8011 - Companyname F1: 0.9437 - County F1: 0.8752 - Creditcardcvv F1: 0.8635 - Creditcardissuer F1: 0.9738 - Creditcardnumber F1: 0.8771 - Currency F1: 0.6542 - Currencycode F1: 0.5566 - Currencyname F1: 0.2214 - Currencysymbol F1: 0.8640 - Date F1: 0.8365 - Dob F1: 0.5696 - Email F1: 0.9914 - Ethereumaddress F1: 0.9903 - Eyecolor F1: 0.9076 - Firstname F1: 0.8759 - Gender F1: 0.9324 - Height F1: 0.9046 - Iban F1: 0.9899 - Ip F1: 0.1137 - Ipv4 F1: 0.8118 - Ipv6 F1: 0.8091 - Jobarea F1: 0.7895 - Jobtitle F1: 0.9806 - Jobtype F1: 0.9056 - Lastname F1: 0.8179 - Litecoinaddress F1: 0.8739 - Mac F1: 1.0 - Maskednumber F1: 0.8319 - Middlename F1: 0.8419 - Nearbygpscoordinate F1: 1.0 - Ordinaldirection F1: 0.9682 - Password F1: 0.9595 - Phoneimei F1: 0.9930 - Phonenumber F1: 0.9807 - Pin F1: 0.7868 - Prefix F1: 0.9355 - Secondaryaddress F1: 0.9967 - Sex F1: 0.9692 - Ssn F1: 0.9898 - State F1: 0.7407 - Street F1: 0.7823 - Time F1: 0.9500 - Url F1: 0.9936 - Useragent F1: 0.9976 - Username F1: 0.9331 - Vehiclevin F1: 0.9713 - Vehiclevrm F1: 0.9493 - Zipcode F1: 0.8634 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_ratio: 0.2 - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Overall Precision \| Overall Recall \| Overall F1 \| Overall Accuracy \| Accountname F1 \| Accountnumber F1 \| Age F1 \| Amount F1 \| Bic F1 \| Bitcoinaddress F1 \| Buildingnumber F1 \| City F1 \| Companyname F1 \| County F1 \| Creditcardcvv F1 \| Creditcardissuer F1 \| Creditcardnumber F1 \| Currency F1 \| Currencycode F1 \| Currencyname F1 \| Currencysymbol F1 \| Date F1 \| Dob F1 \| Email F1 \| Ethereumaddress F1 \| Eyecolor F1 \| Firstname F1 \| Gender F1 \| Height F1 \| Iban F1 \| Ip F1 \| Ipv4 F1 \| Ipv6 F1 \| Jobarea F1 \| Jobtitle F1 \| Jobtype F1 \| Lastname F1 \| Litecoinaddress F1 \| Mac F1 \| Maskednumber F1 \| Middlename F1 \| Nearbygpscoordinate F1 \| Ordinaldirection F1 \| Password F1 \| Phoneimei F1 \| Phonenumber F1 \| Pin F1 \| Prefix F1 \| Secondaryaddress F1 \| Sex F1 \| Ssn F1 \| State F1 \| Street F1 \| Time F1 \| Url F1 \| Useragent F1 \| Username F1 \| Vehiclevin F1 \| Vehiclevrm F1 \| Zipcode F1 \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:-----------------:\|:--------------:\|:----------:\|:----------------:\|:--------------:\|:----------------:\|:------:\|:---------:\|:------:\|:-----------------:\|:-----------------:\|:-------:\|:--------------:\|:---------:\|:----------------:\|:-------------------:\|:-------------------:\|:-----------:\|:---------------:\|:---------------:\|:-----------------:\|:-------:\|:------:\|:--------:\|:------------------:\|:-----------:\|:------------:\|:---------:\|:---------:\|:-------:\|:------:\|:-------:\|:-------:\|:----------:\|:-----------:\|:----------:\|:-----------:\|:------------------:\|:------:\|:---------------:\|:-------------:\|:----------------------:\|:-------------------:\|:-----------:\|:------------:\|:--------------:\|:------:\|:---------:\|:-------------------:\|:------:\|:------:\|:--------:\|:---------:\|:-------:\|:------:\|:------------:\|:-----------:\|:-------------:\|:-------------:\|:----------:\| \| 0.463 \| 1.0 \| 4350 \| 0.3229 \| 0.5378 \| 0.5277 \| 0.5327 \| 0.8941 \| 0.8722 \| 0.7667 \| 0.5849 \| 0.2284 \| 0.5391 \| 0.7502 \| 0.3143 \| 0.1514 \| 0.2844 \| 0.2640 \| 0.0086 \| 0.5288 \| 0.0 \| 0.0956 \| 0.0 \| 0.0 \| 0.3410 \| 0.7146 \| 0.0169 \| 0.8043 \| 0.9458 \| 0.0090 \| 0.4894 \| 0.1550 \| 0.0 \| 0.8653 \| 0.0 \| 0.8168 \| 0.7474 \| 0.1611 \| 0.4548 \| 0.0035 \| 0.3781 \| 0.1472 \| 0.8989 \| 0.4641 \| 0.0035 \| 0.9955 \| 0.0 \| 0.7959 \| 0.9464 \| 0.7831 \| 0.2258 \| 0.7847 \| 0.8639 \| 0.5481 \| 0.7480 \| 0.0643 \| 0.1795 \| 0.7463 \| 0.9683 \| 0.9080 \| 0.4569 \| 0.8724 \| 0.5152 \| 0.5458 \| \| 0.1944 \| 2.0 \| 8700 \| 0.1709 \| 0.7179 \| 0.7495 \| 0.7334 \| 0.9387 \| 0.9789 \| 0.9718 \| 0.6535 \| 0.4640 \| 0.6039 \| 0.9240 \| 0.6723 \| 0.4777 \| 0.8654 \| 0.6234 \| 0.7241 \| 0.8713 \| 0.6077 \| 0.4598 \| 0.0698 \| 0.0104 \| 0.6163 \| 0.7518 \| 0.4439 \| 0.9803 \| 0.9848 \| 0.6276 \| 0.6714 \| 0.7937 \| 0.6295 \| 0.9538 \| 0.0 \| 0.8285 \| 0.7976 \| 0.5304 \| 0.9253 \| 0.6957 \| 0.4694 \| 0.7181 \| 0.9892 \| 0.6301 \| 0.2027 \| 0.9865 \| 0.8016 \| 0.7931 \| 0.9888 \| 0.9658 \| 0.3231 \| 0.8959 \| 0.9721 \| 0.8506 \| 0.9692 \| 0.3841 \| 0.4389 \| 0.9064 \| 0.9905 \| 0.9670 \| 0.8341 \| 0.9563 \| 0.8449 \| 0.7487 \| \| 0.1275 \| 3.0 \| 13050 \| 0.1174 \| 0.8276 \| 0.8506 \| 0.8390 \| 0.9559 \| 0.9881 \| 0.9896 \| 0.7347 \| 0.8484 \| 0.8214 \| 0.9571 \| 0.7815 \| 0.7437 \| 0.9289 \| 0.7794 \| 0.8323 \| 0.9754 \| 0.8624 \| 0.4890 \| 0.4318 \| 0.2006 \| 0.8043 \| 0.8066 \| 0.5459 \| 0.9858 \| 0.9903 \| 0.8511 \| 0.8071 \| 0.8187 \| 0.8657 \| 0.9486 \| 0.0 \| 0.8396 \| 0.8049 \| 0.7326 \| 0.9720 \| 0.8699 \| 0.6714 \| 0.8655 \| 0.9957 \| 0.8194 \| 0.6478 \| 1.0 \| 0.9660 \| 0.9331 \| 0.9916 \| 0.9711 \| 0.6899 \| 0.9302 \| 0.9902 \| 0.9413 \| 0.9847 \| 0.5684 \| 0.7259 \| 0.9381 \| 0.9929 \| 0.9953 \| 0.9094 \| 0.9598 \| 0.9115 \| 0.8324 \| \| 0.0976 \| 4.0 \| 17400 \| 0.1065 \| 0.8624 \| 0.8877 \| 0.8749 \| 0.9598 \| 0.9907 \| 0.9939 \| 0.8312 \| 0.9141 \| 0.8689 \| 0.9511 \| 0.8027 \| 0.8014 \| 0.9538 \| 0.8827 \| 0.8599 \| 0.9701 \| 0.8634 \| 0.6637 \| 0.5488 \| 0.1181 \| 0.8541 \| 0.8224 \| 0.5333 \| 0.9926 \| 0.9876 \| 0.9041 \| 0.8664 \| 0.9303 \| 0.9207 \| 0.9861 \| 0.0591 \| 0.8174 \| 0.8098 \| 0.7798 \| 0.9686 \| 0.9013 \| 0.7845 \| 0.8661 \| 1.0 \| 0.8091 \| 0.8103 \| 1.0 \| 0.9785 \| 0.9430 \| 0.9916 \| 0.9806 \| 0.7778 \| 0.9354 \| 0.9913 \| 0.9692 \| 0.9885 \| 0.7476 \| 0.7658 \| 0.9427 \| 0.9889 \| 0.9976 \| 0.9346 \| 0.9797 \| 0.9570 \| 0.8362 \| \| 0.0886 \| 5.0 \| 21750 \| 0.1055 \| 0.8683 \| 0.8949 \| 0.8814 \| 0.9609 \| 0.9898 \| 0.9939 \| 0.8397 \| 0.9169 \| 0.9012 \| 0.9583 \| 0.8109 \| 0.8011 \| 0.9437 \| 0.8752 \| 0.8635 \| 0.9738 \| 0.8771 \| 0.6542 \| 0.5566 \| 0.2214 \| 0.8640 \| 0.8365 \| 0.5696 \| 0.9914 \| 0.9903 \| 0.9076 \| 0.8759 \| 0.9324 \| 0.9046 \| 0.9899 \| 0.1137 \| 0.8118 \| 0.8091 \| 0.7895 \| 0.9806 \| 0.9056 \| 0.8179 \| 0.8739 \| 1.0 \| 0.8319 \| 0.8419 \| 1.0 \| 0.9682 \| 0.9595 \| 0.9930 \| 0.9807 \| 0.7868 \| 0.9355 \| 0.9967 \| 0.9692 \| 0.9898 \| 0.7407 \| 0.7823 \| 0.9500 \| 0.9936 \| 0.9976 \| 0.9331 \| 0.9713 \| 0.9493 \| 0.8634 \| ### Framework versions - Transformers 4.26.1 - Pytorch 2.0.0.post101 - Datasets 2.10.1 - Tokenizers 0.13.3
AlexandreManai/ppo-SnowballTarget	AlexandreManai	2024-03-10T15:02:27Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2024-03-10T15:02:22Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: AlexandreManai/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
HachiML/myBit-Llama2-jp-127M-test-8	HachiML	2024-03-10T14:59:46Z	7	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "base_model:finetune:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T14:33:58Z	--- license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags: - generated_from_trainer model-index: - name: myBit-Llama2-jp-127M-test-8 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # myBit-Llama2-jp-127M-test-8 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 4.5927 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.00024 - train_batch_size: 96 - eval_batch_size: 96 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: polynomial - lr_scheduler_warmup_steps: 250 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 9.4805 \| 0.04 \| 100 \| 8.6095 \| \| 7.8321 \| 0.07 \| 200 \| 7.0695 \| \| 6.8097 \| 0.11 \| 300 \| 6.5242 \| \| 6.1628 \| 0.15 \| 400 \| 5.9676 \| \| 5.7241 \| 0.18 \| 500 \| 5.5946 \| \| 5.5282 \| 0.22 \| 600 \| 5.4358 \| \| 5.5317 \| 0.26 \| 700 \| 5.3903 \| \| 5.399 \| 0.29 \| 800 \| 5.3153 \| \| 5.2444 \| 0.33 \| 900 \| 5.1738 \| \| 5.1217 \| 0.37 \| 1000 \| 5.0826 \| \| 5.0392 \| 0.4 \| 1100 \| 5.0498 \| \| 5.0022 \| 0.44 \| 1200 \| 4.9668 \| \| 4.9574 \| 0.48 \| 1300 \| 4.9327 \| \| 4.8924 \| 0.51 \| 1400 \| 4.8715 \| \| 4.8545 \| 0.55 \| 1500 \| 4.8475 \| \| 4.8104 \| 0.58 \| 1600 \| 4.8027 \| \| 4.7834 \| 0.62 \| 1700 \| 4.7821 \| \| 4.7563 \| 0.66 \| 1800 \| 4.7486 \| \| 4.7112 \| 0.69 \| 1900 \| 4.7241 \| \| 4.701 \| 0.73 \| 2000 \| 4.7091 \| \| 4.678 \| 0.77 \| 2100 \| 4.6785 \| \| 4.6376 \| 0.8 \| 2200 \| 4.6615 \| \| 4.6264 \| 0.84 \| 2300 \| 4.6454 \| \| 4.6032 \| 0.88 \| 2400 \| 4.6245 \| \| 4.5949 \| 0.91 \| 2500 \| 4.6137 \| \| 4.5861 \| 0.95 \| 2600 \| 4.5992 \| \| 4.5783 \| 0.99 \| 2700 \| 4.5927 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
gdupont/TinyLlama-1.1B-Chat-colors-v1.0_peft	gdupont	2024-03-10T14:56:49Z	91	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T14:55:18Z	--- 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]
drMostert/segformer-b0-scene-parse-150	drMostert	2024-03-10T14:54:08Z	22	0	transformers	[ "transformers", "tensorboard", "safetensors", "segformer", "generated_from_trainer", "dataset:scene_parse_150", "base_model:nvidia/mit-b0", "base_model:finetune:nvidia/mit-b0", "license:other", "endpoints_compatible", "region:us" ]	null	2024-03-10T14:37:22Z	--- license: other base_model: nvidia/mit-b0 tags: - generated_from_trainer datasets: - scene_parse_150 model-index: - name: segformer-b0-scene-parse-150 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # segformer-b0-scene-parse-150 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset. It achieves the following results on the evaluation set: - Loss: 3.5433 - Mean Iou: 0.0600 - Mean Accuracy: 0.1407 - Overall Accuracy: 0.4130 - Per Category Iou: [0.4725842300574752, 0.23752185781261304, 0.500907459865348, 0.26304551026233747, 0.20113818567783023, 0.2773168787458298, 0.41824906409273377, nan, 0.0, nan, 0.0011588462105728914, 0.0, 0.07620455691560078, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.09211967767850622, 0.21158826718063, 0.0, 0.009009009009009009, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] - Per Category Accuracy: [0.7019862011289986, 0.2599706832653203, 0.974451706755296, 0.7671708061606771, 0.8256484417005024, 0.9195901184609862, 0.558454659058402, nan, 0.0, nan, 0.0012131371727286764, 0.0, 0.08718056302201477, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.7549277791078126, 0.3302933433621662, nan, 0.009011546043368065, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Mean Iou \| Mean Accuracy \| Overall Accuracy \| Per Category Iou \| Per Category Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:-------------:\|:----------------:\|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:\|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:\| \| 4.2364 \| 1.0 \| 20 \| 4.1492 \| 0.0409 \| 0.1240 \| 0.3995 \| [0.5322293849075467, 0.23690897692857837, 0.4397872027790232, 0.19607643898903274, 0.36383498030038486, 0.12773088147613518, 0.009777174103954194, nan, 0.0, nan, 0.11339002834750708, 0.0, 0.1422973407586709, 9.40875390463287e-06, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08988905804476369, 0.44466963923794084, nan, 0.0009037191518943343, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan] \| [0.8962503067930806, 0.259095816281796, 0.589595813676267, 0.7087472147177173, 0.7379164580899938, 0.3320823679143687, 0.01257170387991388, nan, 0.0, nan, 0.11999029490261817, 0.0, 0.22044921132337708, 0.0012360939431396785, 0.0, 0.0, 0.0, nan, 0.0, 0.8528449445375469, 0.7219819481007897, nan, 0.0018304702900591382, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 4.2734 \| 2.0 \| 40 \| 3.9214 \| 0.0500 \| 0.1198 \| 0.3713 \| [0.5414063519948691, 0.19841541146471395, 0.5368811396588854, 0.1932222222222222, 0.19532902970225716, 0.1522866572371523, 0.0, nan, 0.0008067375886524823, nan, 0.00181349238333199, 0.0, 0.05775538617646365, 0.0008988949791032748, 0.0, 0.0, 0.0, 0.0, 0.0, 0.07665371555439467, 0.5463317251705208, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.7765582815951422, 0.23428088058355365, 0.7064269767347887, 0.7664607122160645, 0.804457051745555, 0.3320334170936266, 0.0, nan, 0.0008153902672867217, nan, 0.0019851335553741976, 0.0, 0.06418241179015825, 0.21508034610630408, 0.0, 0.0, 0.0, nan, 0.0, 0.7494214348415928, 0.6175253854832644, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 3.4296 \| 3.0 \| 60 \| 3.9287 \| 0.0500 \| 0.1247 \| 0.3684 \| [0.504898336414048, 0.16609815628654262, 0.461471733451624, 0.22065343315487834, 0.16518809916592642, 0.28398331595411885, 0.1604012425930234, nan, 0.0011706985763947845, nan, 0.02186771822907331, 0.0, 0.037805308927614856, 0.00042000840016800337, 0.0, 0.0, 0.0, 0.0, 0.0, 0.059326658998615056, 0.4647721010784854, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.6853021116454109, 0.19175037128736774, 0.9458424673448566, 0.7632938564630792, 0.7964291673619223, 0.44437555069673335, 0.17647058823529413, nan, 0.0011738035715885774, nan, 0.024218629375565213, 0.0, 0.043491942779970365, 0.0519159456118665, 0.0, 0.0, 0.0, nan, 0.0, 0.8067592370920118, 0.5550959007145544, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 3.6539 \| 4.0 \| 80 \| 3.9424 \| 0.0460 \| 0.1303 \| 0.3287 \| [0.37671262071262074, 0.13443477431760276, 0.4269336776273018, 0.1963029676535461, 0.14844067652609796, 0.2914056148070209, 0.1012685049158097, nan, 0.0, nan, 0.015320700804571772, 0.0, 0.04650892929668009, 0.0008672882232266457, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08581872964530209, 0.4295496258647466, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.5141706587642829, 0.14704138526399546, 0.9420238612371071, 0.7765326194304557, 0.9070026141609656, 0.7953529354175505, 0.10793598217377558, nan, 0.0, nan, 0.01797648719588857, 0.0, 0.05255221786618065, 0.12855377008652658, 0.0, 0.0, 0.0, nan, 0.0, 0.7728034474503231, 0.572113576532531, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 3.8072 \| 5.0 \| 100 \| 3.6808 \| 0.0524 \| 0.1296 \| 0.3789 \| [0.49848536561886225, 0.15669095400920174, 0.5116626603724406, 0.2285989936984026, 0.16470623593542788, 0.29551710026963546, 0.1565518949715135, nan, 0.0, nan, 0.0009195500620161669, 0.0, 0.05793396722251421, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0683129055515501, 0.32468649229666785, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.7248861456789899, 0.16903666136853918, 0.8923819818363656, 0.7639060064153315, 0.8128371989543356, 0.8601801390203309, 0.1712762914226351, nan, 0.0, nan, 0.0009484526986787834, 0.0, 0.06359237940393617, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.816614795307637, 0.42600601729973675, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 4.0198 \| 6.0 \| 120 \| 3.7189 \| 0.0502 \| 0.1318 \| 0.3460 \| [0.39116293372838296, 0.13864719866417147, 0.40087800798076706, 0.2157543281871196, 0.16127116562617994, 0.3785288215728855, 0.20748449345279119, nan, 0.0, nan, 0.0037886043888214886, 0.0, 0.0654386250902401, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08008943702143075, 0.3613156909249782, nan, 0.006734878901696671, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.5573253097473843, 0.14608733605900429, 0.9829021406418895, 0.7742635836074405, 0.8156367614068265, 0.8987697027053487, 0.22663695629262712, nan, 0.0, nan, 0.00392615303174008, 0.0, 0.07368848912373635, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.7674966084111404, 0.544283565250094, nan, 0.007321881160236553, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 3.3227 \| 7.0 \| 140 \| 3.5359 \| 0.0534 \| 0.1315 \| 0.4101 \| [0.4770347521615892, 0.24974336818456752, 0.5108344403430883, 0.2366895974550102, 0.17451872484087896, 0.3132020145632557, 0.19149852704129844, nan, 0.0, nan, 0.0, 0.0, 0.07627803718584476, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08870909519706982, 0.24312130647518587, 0.0, 0.001126443255421008, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.7282076920979192, 0.2790960866601132, 0.9653547363848508, 0.7663709302230675, 0.8270945732984779, 0.8330777012694579, 0.20748580978334513, nan, 0.0, nan, 0.0, 0.0, 0.08289299434880092, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.7354161679035991, 0.3597216998871756, nan, 0.001126443255421008, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 2.7606 \| 8.0 \| 160 \| 3.5593 \| 0.0594 \| 0.1378 \| 0.4101 \| [0.491183620322603, 0.23218100723379267, 0.5228177173827064, 0.24633373487665636, 0.20350864022596432, 0.2936651680126143, 0.3681167890630956, nan, 0.0, nan, 2.0947672713561523e-05, 0.0, 0.056203414282279394, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.07741366689718485, 0.23988607300627762, nan, 0.001126443255421008, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.7214700615404194, 0.2512355323459375, 0.968173231369142, 0.7677584701148393, 0.8041604093664831, 0.8995202819567275, 0.4362155407338262, nan, 0.0, nan, 2.2057039504157753e-05, 0.0, 0.061297809013072496, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.7637858111882532, 0.3880218127115457, nan, 0.001126443255421008, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 3.1471 \| 9.0 \| 180 \| 3.5223 \| 0.0611 \| 0.1404 \| 0.4096 \| [0.4694048515016408, 0.2304776927428032, 0.5069242587551356, 0.25709018097468106, 0.21042235106866758, 0.26575785951918235, 0.40512733060482037, nan, 0.0, nan, 0.0, 0.0, 0.07140409542602592, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.089745061462668, 0.23717794365518902, nan, 0.007744297381019431, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.7018880273432174, 0.24945296672608552, 0.9716180585721645, 0.7671136721651336, 0.8235719450469993, 0.9215318343504226, 0.5365181649829115, nan, 0.0, nan, 0.0, 0.0, 0.07923479355422397, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.7486633149788524, 0.37044001504324936, nan, 0.007744297381019431, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| \| 2.7459 \| 10.0 \| 200 \| 3.5433 \| 0.0600 \| 0.1407 \| 0.4130 \| [0.4725842300574752, 0.23752185781261304, 0.500907459865348, 0.26304551026233747, 0.20113818567783023, 0.2773168787458298, 0.41824906409273377, nan, 0.0, nan, 0.0011588462105728914, 0.0, 0.07620455691560078, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.09211967767850622, 0.21158826718063, 0.0, 0.009009009009009009, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| [0.7019862011289986, 0.2599706832653203, 0.974451706755296, 0.7671708061606771, 0.8256484417005024, 0.9195901184609862, 0.558454659058402, nan, 0.0, nan, 0.0012131371727286764, 0.0, 0.08718056302201477, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.7549277791078126, 0.3302933433621662, nan, 0.009011546043368065, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan] \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Jackline/Blip2-HateSpeech-PEFT-Whole-2.7b	Jackline	2024-03-10T14:53:53Z	1	0	peft	[ "peft", "arxiv:1910.09700", "base_model:Salesforce/blip2-opt-2.7b", "base_model:adapter:Salesforce/blip2-opt-2.7b", "region:us" ]	null	2024-03-10T14:53:46Z	--- library_name: peft base_model: Salesforce/blip2-opt-2.7b --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - 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 Data 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 Data 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] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.1
ankursinghbisht/a2c-PandaPickAndPlace-v3	ankursinghbisht	2024-03-10T14:53:41Z	0	0	stable-baselines3	[ "stable-baselines3", "PandaPickAndPlace-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-03-10T14:49:30Z	--- library_name: stable-baselines3 tags: - PandaPickAndPlace-v3 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaPickAndPlace-v3 type: PandaPickAndPlace-v3 metrics: - type: mean_reward value: -50.00 +/- 0.00 name: mean_reward verified: false --- # A2C Agent playing PandaPickAndPlace-v3 This is a trained model of a A2C agent playing PandaPickAndPlace-v3 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
afaji/fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-5	afaji	2024-03-10T14:48:45Z	89	0	transformers	[ "transformers", "pytorch", "bert", "multiple-choice", "generated_from_trainer", "endpoints_compatible", "region:us" ]	multiple-choice	2024-03-10T14:48:13Z	--- tags: - generated_from_trainer metrics: - accuracy model-index: - name: fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa-loop-5 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4393 - Accuracy: 0.5202 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 16 - eval_batch_size: 16 - seed: 321 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 63 \| 2.3938 \| 0.2475 \| \| No log \| 2.0 \| 126 \| 1.5164 \| 0.3636 \| \| No log \| 3.0 \| 189 \| 1.1653 \| 0.4646 \| \| No log \| 4.0 \| 252 \| 0.7958 \| 0.4394 \| \| No log \| 5.0 \| 315 \| 0.5525 \| 0.4596 \| \| No log \| 6.0 \| 378 \| 1.1572 \| 0.4747 \| \| No log \| 7.0 \| 441 \| 0.3450 \| 0.4798 \| \| 1.7802 \| 8.0 \| 504 \| 0.4393 \| 0.5202 \| \| 1.7802 \| 9.0 \| 567 \| 0.5459 \| 0.4343 \| \| 1.7802 \| 10.0 \| 630 \| 0.4935 \| 0.5101 \| \| 1.7802 \| 11.0 \| 693 \| 0.3405 \| 0.4697 \| \| 1.7802 \| 12.0 \| 756 \| 0.3275 \| 0.4697 \| \| 1.7802 \| 13.0 \| 819 \| 0.2442 \| 0.4646 \| \| 1.7802 \| 14.0 \| 882 \| 0.2561 \| 0.4495 \| \| 1.7802 \| 15.0 \| 945 \| 0.2196 \| 0.4495 \| \| 0.215 \| 16.0 \| 1008 \| 0.1943 \| 0.4495 \| \| 0.215 \| 17.0 \| 1071 \| 0.1845 \| 0.4545 \| \| 0.215 \| 18.0 \| 1134 \| 0.1702 \| 0.4444 \| \| 0.215 \| 19.0 \| 1197 \| 0.1788 \| 0.4545 \| \| 0.215 \| 20.0 \| 1260 \| 0.1747 \| 0.4545 \| ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0
dilip025/llama-2-7b	dilip025	2025-09-04T09:43:11Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "facebook", "meta", "llama-2", "en", "base_model:meta-llama/Llama-2-7b-chat-hf", "base_model:finetune:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "autotrain_compatible", "text-generation-inference", "region:us" ]	text-generation	2024-03-02T17:03:29Z	--- language: - en license: llama2 tags: - facebook - meta - pytorch - llama - llama-2 model_name: Llama 2 7B Chat arxiv: 2307.09288 base_model: meta-llama/Llama-2-7b-chat-hf inference: false model_creator: Meta Llama 2 model_type: llama pipeline_tag: text-generation prompt_template: '[INST] <<SYS>> You are NutriLife chatbot, you are going to get questions related to food, nutrition, health, and diet by the users from Nepal. Answer them very shortly and accurately if the message is only about food, nutrition, and diet. Otherwise, ignore. <</SYS>> {prompt}[/INST] ' quantized_by: Dilip Pokhrel --- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Llama 2 7B Chat -- Food and Nutrition <br> - Model creator: [Meta Llama 2] <br> - Original model: [Llama 2 7B Chat] <a href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf">Original Model</a> <br> - Fine Tuned by: [Dilip Pokhrel] <a href="https://dilippokhrel.com.np">Profile</a> #### Simple example code to load one of these GGUF models ```python # Load model directly or use qunatization technique if you have low gpu ram from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dilip025/llama-2-7b") model = AutoModelForCausalLM.from_pretrained("dilip025/llama-2-7b") system_message = 'You are NutriLife chatbot, you are going to get questions related to food, nutrition, health, and diet by the users from Nepal. Answer them very shortly and accurately if the message is only about food, nutrition, and diet. Otherwise, ignore.' prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n Tell me some of the famous Nepali food recipes [/INST]" num_new_tokens = 200 # Change to the number of new tokens you want to generate # Count the number of tokens in the prompt num_prompt_tokens = len(tokenizer(prompt)['input_ids']) # Calculate the maximum length for the generation max_length = num_prompt_tokens + num_new_tokens gen = pipeline('text-generation', model=model, tokenizer=tokenizer, max_length=max_length) result = gen(prompt) print(result[0]['generated_text'].replace(prompt, '')) ``` ## Ethical Considerations and Limitations Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
turgutburak01/ppo-LunarLander-v2	turgutburak01	2024-03-10T14:39:03Z	1	0	stable-baselines3	[ "stable-baselines3", "tensorboard", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-02-03T13:52:41Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 252.49 +/- 23.50 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
SHONOSUKE/Addtional_Trained_BERT_For_Legal_Domain_v1	SHONOSUKE	2024-03-10T14:36:31Z	194	0	transformers	[ "transformers", "safetensors", "bert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-03-10T14:36:14Z	--- 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]
CaptainPollutionTV/DoctorBlight-OJ4	CaptainPollutionTV	2024-03-10T14:33:06Z	0	0	null	[ "DreamBooth", "OpenJourney4", "license:cc", "region:us" ]	null	2024-03-10T10:47:13Z	--- license: cc tags: - DreamBooth - OpenJourney4 --- Made by CaptainPollutionTV using the getimg.ai Dreambooth tool. Details about the model: Base Model Openjourney v4 Instance prompt doctorblight Class prompt a woman Learning Rate 0.000001 Learning Rate Scheduler polynomial Training Steps 10000 (200 steps warmup) Class images 1000 Model seed 327558656 Sample images: ![16 - img-WtUY4DZ4DeeKfmvNdb020P.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/SX1WkHp9jk7sBEHPyJJn_.png) ![17 - img-QvgsqfQtgQ5sJsVeo65eO1.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/AuQwnGgbXTLgV0D8dqgBE.png) ![18 - img-YDR991oq4BXGgUEUhw5md8.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/YN05X_SQ4gjf1DPl2U3xX.png) ![19 - img-45r9C4b3GeLhTLH0qcJZip.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/H3tzm4KV-NJxvCsolnVxp.png) ![20 - img-cfrO54S0PmsA6whmDXoY8N.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/YVKTYUQ1gnNBF3nuogIUi.png) ![21 - img-lJBoFmNgF0B7aXUYi1e4Lt.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/8oRXPlcumF7sRY_2Yb9zT.png) ![22 - img-PkkNB67ukM8raaXQFB4hxv.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/bSxvvbiZQjhbqf-lQtMeI.png) ![23 - img-3UciX3JFXCfbNVCDMWFeoC.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/I8XZV4tAeBNyU0DuOV_B9.png) ![24 - img-J8ZzGpNZt2C6sMfOppAtdm.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/h272h1tewrXMOqdjCL959.png) ![25 - img-uRgXg4Ww7m1Q6TkWqxHwzu.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/CC1EN9ypA2TUA2CUlGgT2.png) ![26 - img-YAOgtEaFk4SOzbVSmjpK8C.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/s5zeH9L7kUfx6tC1mhCWi.png) ![27 - img-eQ9c6OdPW5C6sKywpSqbNb.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/n007HxPTn5REaVJSGEBBV.png) ![28 - img-Ijkx2ITZLp0zfvscwYZM7O.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/gOTvopEFgVt5UM6JBFn78.png) ![29 - img-yrrA1sjm6FuLBem1T9ViWv.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/UPCHUll--nj6v6WNknNtL.png) ![30 - img-aKj25IHaOEBLFs6Z4pCXHG.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/NvgR4oN8bISSw5zYXsg4L.png) ![31 - img-42BGKfNH8lfQCxBNlKfzuj.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/bjYYu9lAgoyAnuQtFcaUU.png) ![32 - img-l1SOKcyL5yplgQU5xB3QDp.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/iTI-OaeQoEKasMB6fNtHs.png) ![33 - img-XmXi4OFuMLfHDz6b0LC3SS.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/RtMiXeeLYOG1HecZAjrWQ.png) ![34 - img-d0LQduVHqPfOAMh1xSCVcz.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/zh6v4xc79d-wXPerIYTmd.png) ![35 - img-bWocvMy5WQrap6mvbUjJmf.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/hOY5TX2fV3NsQgxFWfloc.png) ![36 - img-ljVs0JzLvNWpWvkeDfhoRG.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/qVqUpqPQ5byTq6pj6Pri1.png) ![37 - img-Y3u4jWqDzZhe3wPcg2UTWD.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/8QegydFzucjJphmZkXiEH.png) ![38 - img-p9JlbGnOxF286kdMzPa8Bd.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/uWPvtvslUyjfS1NZmegYT.png) ![39 - img-khILBi51kTrYuZt4KmEZwD.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/5mEwG8YS3EY5DWu2Bibtw.png) ![40 - img-yZyZThDzJr4ARV3Xg1CZ8y.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/8pExmoqbtRSge4MVpRkII.png) ![41 - img-fcVispUnk4p2z3C7WbaHWF.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/CWikoawmBdb3Bb5QM-sjC.png) ![42 - img-qroyXbWkIwTq8y4ueQS2Od.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/HDjlRxzlUtvdaOBZFZB-u.png) ![43 - img-BEdWjHiP68KaeYYuKddozc.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/LZQT3IXoiZTvaYRruwUfz.png) ![44 - img-5DooyelX3MMkenET2vPL8O.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/LiB8LwC6oaFiDO6d1AqPw.png) ![45 - img-DOTAhDY2iM030aZ1F0QCDp.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/VYV_mMb4ANIrL0u9zsaFv.png) ![46 - img-iimAyNQ3CRDmlcuO2uw9nH.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/3eKVBG16JAIbsn7zqxKGP.png) ![47 - img-6ow55jlmPy931Sq1zqm1vK.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/XdX4AO5D909p5nEiTE_AU.png) ![48 - img-GVWOiznV8D1o89QfsUbH0R.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/nEkUDmdbcnnFlvAi1gaSX.png) ![49 - img-x9pHDrJeYTnTb0cobDUgA1.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/Jy1zwWbH1p_KDafr8IZnB.png) ![50 - img-YcHBzBuMFCYT62tM52D3OI.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/lIFXSoYA529uT5J-6qZe7.png) ![51 - img-TPkQ3lHEFpBQbB2b5RMGWe.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/z1-eRt0TWOBApUNpl78cw.png) ![52 - img-B4AYBFziTcG9QycQzUIsnn.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/PEH99Bh_LOMTGzc8SNt2L.png) ![53 - img-fYtI9TULEQaTZAdCJHMluh.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/MhtPgDl8AiAKZfznuuhxQ.png) ![54 - img-4iMlrzHcG0AiRz8XikeYMt.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/Y47cTlQqVTFwtM_EWL8Dz.png) ![55 - img-Es3Lz4p9kSXDk5Jyk3XgnA.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/Gl7tBYpzkfbtHIPApQFKo.png) ![56 - img-YdDExQ9ehfeIXcdJ9OzGMK.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/gGpwPoO3p_qm6F_qR4btR.png) ![57 - img-HYj721R1WfcNtvucfmrSds.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/QCd_lZCjB9y6PbVaW8W71.png) ![58 - img-8XBDCa4MZcDOqgqD0mMr9d.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/08q09_fLHAuWBVjy3BmGz.png) ![59 - img-kpZyPkqzU7SKGPZkW4OJCT.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/0VI_8-0loRuhK7C54vfbs.png) ![60 - img-AA1S6oXgYsMGp5S5UrS8u7.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/9FYHV0Xi_0YqR6BswUqzv.png) ![61 - img-MxRM78gRGe9uifnHBEQXaA.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/U8HJBPv3bHuJXyVubjHO2.png) ![62 - img-EFwdKI2XdFairGkpMODjkY.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/IbmQjsdKZt-0aL7oju3Sf.png) ![63 - img-ULc9QU52GYa7EQIuM7mhnn.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/4QwNU-9CVEB_Jxmh_peRi.png) ![64 - img-I9GZrbfSvwJIbKp2CN514Q.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/wAZGaImw1Q8z36eVHOcRu.png) ![65 - img-rqMd0CQO6mGtPRMGz58Ga7.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/k3ADEId5IjxoVvwioAlGb.png) ![66 - img-uOvQcLGepoHtrS4iuxF0xq.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/hsnCRP-h5zz2hWtCF8BiV.png) ![67 - img-xjFTifdS5pxxiURwFKJ9qc.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/vNaBCfSlOB-jCzTBiehnQ.png) ![68 - img-orj1guSeRvBDZF5qjmuvX5.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/-XktyDvFOwzR1OEqdwQjW.png) ![69 - img-vL0obBFX8BuhF0ipXygbxj.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/6ms-T2QBlQZGVt--K1SL0.png) ![70 - img-7B1pRA747uyDmQwiN8XBpc.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/iHtpthbMv3zH77iOf5etc.png) ![71 - img-9xnDF3CikYuj9UFwAqjSZc.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/ld7DE65LI5F8mXGj2i_hZ.png) ![72 - img-wkxydvJo7HjLvqLfcstCKg.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/dHuMVisUNAf80QCkK4KAU.png) ![73 - img-p7r4ciUOGwyUFTBTaYI2FX.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/6es1Uyuxo6CUarePwYgvh.png) ![74 - img-BuURGpPXBln8OFK1Gs2qqD.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/jPfTMFg-LukJwLGHwdbvm.png) ![75 - img-J50UL1fVlMTUMgLH2bzdyV.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/a2q3FRKrqKU4dCl4RS63v.png) ![76 - img-9v2hKhZ5I7xyrQr8hFeZ3b.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/CjRRtz_2sMLtV_2SkkwD0.png) ![1 - img-32X4zy54hH3HDPE6m04MC4.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/hMr4aQG2oU2BYi2J0m9Jt.png) ![2 - img-fFGaZCM35R1P9xRxkV8lHd.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/MVRHV5ZmOiNdalrhN4xrl.png) ![3 - img-gbpiUp3F5eMFGXLQCkjiX2.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/NuvFuHoLSBC0pGjEnvWAh.png) ![4 - img-ey2Ya0hwSUwfCSPbM4Eds7.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/0gL0RaWDFYbSlwXqb-eFe.png) ![5 - img-3ai0ctJncZRM85Eesb7iUs.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/J4mId2GxUeWvzvECpQbfq.png) ![6 - img-RYMfMZUEHKwJBPuMSYWrEY.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/QQBWUvc7szobEfRVj6JE_.png) ![7 - img-N5txXhP4btDJE0Pcp5UeWY.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/pyE8ngyC-RjPzGeCf5DW8.png) ![8 - img-awqIdtTmSJxGvp3v97DF2I.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/rW8E41wXBs79vmURSMW-o.png) ![9 - img-pTZWWTvB3sPq8tvRTRBpil.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/4VDI_USlvElhoAryxOX6M.png) ![10 - img-pB8rpN7IEY2yZ8a5m0EY51.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/3iD_qHlbPsVSEVFo4qwGT.png) ![11 - img-abDysjutoj49S7eFnAk6oY.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/HnmZw0jpOddNzJsfl8EVq.png) ![12 - img-JvreWZwlabMHY8gBMQN9xG.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/FDQs3ZMdZCzL1hz6ihsbm.png) ![13 - img-emEh4KDV20ww43eivghB2U.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/RxhIDmgsgXRakKi98SR8H.png) ![14 - img-lV7AZV8IxrHYls8xGWk5Sd.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/fNI7DCuo0SDIwtdFPTpqk.png) ![15 - img-oY8f1uZuq7KfgbMQk7aOih.png](https://cdn-uploads.huggingface.co/production/uploads/64e35e94c967354314367535/5WJ-S2ru_O3VcZ7BxCxOd.png)
Benevolent/NyanchtaStyle	Benevolent	2024-03-10T14:26:50Z	3	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:playgroundai/playground-v2.5-1024px-aesthetic", "base_model:adapter:playgroundai/playground-v2.5-1024px-aesthetic", "region:us" ]	text-to-image	2024-03-10T14:26:05Z	--- tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora widget: - text: >- (best quality), (masterpiece), (highres), (depth of field), perfect lighting, detailed face, 1 girl, detailed eyes, (looking at viewer),(sharp focus) <lora:eula2-000009:0.8>, euladef, eularnd, yellow eyes, light blue hair, large breasts, hair down,<lora:Nyantcha:1>, <lora:Single bare shoulder shirt:1>, single bare shoulder shirt long, naked shirt, cleavage, bottomless, arms behind back, smile, looking at viewer, sitting on bed, bedroom, house, indoors, morning time, parameters: negative_prompt: >- ng_deepnegative_v1_75t, easynegative, negative_hand, negative_hand-neg, lowres, (bad anatomy, bad proportions), blurry, text, error, missing fingers, missing arms, missing legs, short legs, extra digit, 2girls, out of frame, petite, distorted perspective, watermark, artist name, username,(censoring, censorship, white bars, black bars), head piece, hair accessory, output: url: images/00029-3736919457.png base_model: playgroundai/playground-v2.5-1024px-aesthetic instance_prompt: <lora:Nyantcha:1> --- # ThiccWithaQ <Gallery /> ## Trigger words You should use `<lora:Nyantcha:1>` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/Benevolent/NyanchtaStyle/tree/main) them in the Files & versions tab.
hamzasidat/results	hamzasidat	2024-03-10T14:25:37Z	178	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T01:59:29Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - emotion metrics: - accuracy model-index: - name: results results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion config: split split: validation args: split metrics: - name: Accuracy type: accuracy value: 0.9455 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # results This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.1364 - Accuracy: 0.9455 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.5105 \| 1.0 \| 500 \| 0.1809 \| 0.936 \| \| 0.1462 \| 2.0 \| 1000 \| 0.1364 \| 0.9455 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
Holarissun/gpt2-airl_sft-imdb-seqsampler	Holarissun	2024-03-10T14:20:17Z	2	0	peft	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:lvwerra/gpt2-imdb", "base_model:adapter:lvwerra/gpt2-imdb", "region:us" ]	null	2024-03-10T14:20:15Z	--- library_name: peft tags: - trl - sft - generated_from_trainer base_model: lvwerra/gpt2-imdb model-index: - name: gpt2-airl_sft-imdb-seqsampler results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gpt2-airl_sft-imdb-seqsampler This model is a fine-tuned version of [lvwerra/gpt2-imdb](https://huggingface.co/lvwerra/gpt2-imdb) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
alex-atelo/unigram-tokenizer	alex-atelo	2024-03-10T14:15:31Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-03-10T14:15:30Z	--- 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]
HachiML/myBit-Llama2-jp-127M-test-7	HachiML	2024-03-10T14:15:26Z	7	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "base_model:finetune:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-10T13:46:58Z	--- license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags: - generated_from_trainer model-index: - name: myBit-Llama2-jp-127M-test-7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # myBit-Llama2-jp-127M-7 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 10.6539 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.00024 - train_batch_size: 96 - eval_batch_size: 96 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: polynomial - lr_scheduler_warmup_steps: 250 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 9.0536 \| 0.04 \| 100 \| 7.4802 \| \| 6.8962 \| 0.07 \| 200 \| 6.5875 \| \| 6.3685 \| 0.11 \| 300 \| 6.1149 \| \| 5.8698 \| 0.15 \| 400 \| 5.6208 \| \| 5.6334 \| 0.18 \| 500 \| 6.1096 \| \| 8.8705 \| 0.22 \| 600 \| 10.3915 \| \| 10.5174 \| 0.26 \| 700 \| 10.5752 \| \| 10.5929 \| 0.29 \| 800 \| 10.6066 \| \| 10.6128 \| 0.33 \| 900 \| 10.6187 \| \| 10.6218 \| 0.37 \| 1000 \| 10.6255 \| \| 10.6274 \| 0.4 \| 1100 \| 10.6302 \| \| 10.6312 \| 0.44 \| 1200 \| 10.6335 \| \| 10.6343 \| 0.48 \| 1300 \| 10.6363 \| \| 10.6369 \| 0.51 \| 1400 \| 10.6384 \| \| 10.6391 \| 0.55 \| 1500 \| 10.6404 \| \| 10.6408 \| 0.59 \| 1600 \| 10.6422 \| \| 10.6426 \| 0.62 \| 1700 \| 10.6438 \| \| 10.6441 \| 0.66 \| 1800 \| 10.6451 \| \| 10.6454 \| 0.7 \| 1900 \| 10.6464 \| \| 10.6467 \| 0.73 \| 2000 \| 10.6477 \| \| 10.6479 \| 0.77 \| 2100 \| 10.6486 \| \| 10.649 \| 0.81 \| 2200 \| 10.6496 \| \| 10.6499 \| 0.84 \| 2300 \| 10.6506 \| \| 10.6508 \| 0.88 \| 2400 \| 10.6515 \| \| 10.6516 \| 0.92 \| 2500 \| 10.6522 \| \| 10.6524 \| 0.95 \| 2600 \| 10.6531 \| \| 10.6534 \| 0.99 \| 2700 \| 10.6539 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
sssy95/dobae	sssy95	2024-03-10T14:12:23Z	47	0	sentence-transformers	[ "sentence-transformers", "safetensors", "xlm-roberta", "feature-extraction", "sentence-similarity", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-10T13:38:13Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) ## Training The model was trained with the parameters: DataLoader: `torch.utils.data.dataloader.DataLoader` of length 324 with parameters: ``` {'batch_size': 2, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` Loss: `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters: ``` {'scale': 20.0, 'similarity_fct': 'cos_sim'} ``` Parameters of the fit()-Method: ``` { "epochs": 2, "evaluation_steps": 50, "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 64, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
another-symato/finetune_bge_m3	another-symato	2024-03-10T14:06:04Z	47	0	sentence-transformers	[ "sentence-transformers", "pytorch", "xlm-roberta", "feature-extraction", "sentence-similarity", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-03-10T14:05:23Z	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity --- # another-symato/finetune_bge_m3 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('another-symato/finetune_bge_m3') embeddings = model.encode(sentences) print(embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [https://seb.sbert.net](https://seb.sbert.net?model_name=another-symato/finetune_bge_m3) ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
sujith013/whisper-medium-tamil	sujith013	2024-03-10T14:05:02Z	62	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "ta", "base_model:openai/whisper-medium", "base_model:finetune:openai/whisper-medium", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-02-24T09:48:50Z	--- language: - ta license: apache-2.0 base_model: openai/whisper-medium tags: - generated_from_trainer metrics: - wer model-index: - name: ./whisper-medium-tamil-openslr results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-medium-tamil This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1628 - Wer: 35.6581 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 10 - training_steps: 100 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\| \| 0.9386 \| 0.15 \| 25 \| 0.5501 \| 43.7602 \| \| 0.3073 \| 0.31 \| 50 \| 0.2054 \| 40.3324 \| \| 0.174 \| 0.46 \| 75 \| 0.1713 \| 36.8452 \| \| 0.1539 \| 0.62 \| 100 \| 0.1628 \| 35.6581 \| ### Framework versions - Transformers 4.37.0 - Pytorch 2.1.2 - Datasets 2.1.0 - Tokenizers 0.15.1
phamsonn/dummy	phamsonn	2024-03-10T13:59:08Z	93	0	transformers	[ "transformers", "safetensors", "camembert", "text-classification", "en", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-03-10T11:15:16Z	--- license: mit language: - en --- # My dummy model This is just a dummy model to test the upload file and model function of Hugging Face
herutriana44/llama-2-7b-drug-sequence-summarizer	herutriana44	2024-03-10T13:58:11Z	1	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-03-08T08:58:06Z	--- 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]

Subsets and Splits

Filtered Qwen2.5 Distill Models

Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.

Filtered Model Cards Count

Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.

Filtered Distill Qwen 7B Models

Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.

Filtered Qwen-7b Model Cards

The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.

Filtered Qwen 7B Model Cards

The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.

Qwen 7B Distilled Models

The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.

Qwen 7B Distilled Model Cards

The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.

Qwen 7B Distilled Models

Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.

Distilled Qwen 7B Models

The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.

Filtered Model Cards with Distill Qwen2.

Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.

Filtered Model Cards with Distill Qwen 7

The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.

Distill Qwen 7B Model Cards

The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.