Datasets:

---

ftopal

/

huggingface-models-processed

like 0

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

[]

[]

[ "# results01\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.30.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.13.3" ]

[ "TAGS\n#pytorch #generated_from_trainer #license-apache-2.0 #region-us \n", "# results01\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.30.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.13.3" ]

[ 24, 29, 7, 9, 9, 4, 108, 5, 47 ]

[ "TAGS\n#pytorch #generated_from_trainer #license-apache-2.0 #region-us \n# results01\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m on the None dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 2### Training results### Framework versions\n\n- Transformers 4.30.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.13.3" ]

[ "transformers", "tensorboard", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-tiny-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 75, 142, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-tiny-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 3### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ 5 ]

[ "TAGS\n#region-us \n" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 32, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "en", "th", "dataset:wannaphong/mark13", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "th" ]

[ "## NumFaLM 3B\nNumFaLM 3B is a bilingual language model trained in Thai and English. The architecture model is Llama model that pretraining from scratch. It was built to open source AI and research for bilingual language models and improve small language models. We released the training script and train datasets so you can research the training and datasets.\n\n- GitHub: URL\n- Training script: URL\n- Train Datasets: wannaphong/mark13\n\n\nWe fork EasyLM and added training by HuggingFace datasets, but HuggingFace was down many times during the time we trained the model, so we can train just one epoch. The model trained one epoch.", "# Acknowledgements\n\nResearch supported with Cloud TPUs from Google's TPU Research Cloud (TRC). We use TPU4-64 for training model about 4 days / 1 epoch.\n\nThank you TPU Research Cloud and EasyLM project! We use EasyLM for pretraining model." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #en #th #dataset-wannaphong/mark13 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## NumFaLM 3B\nNumFaLM 3B is a bilingual language model trained in Thai and English. The architecture model is Llama model that pretraining from scratch. It was built to open source AI and research for bilingual language models and improve small language models. We released the training script and train datasets so you can research the training and datasets.\n\n- GitHub: URL\n- Training script: URL\n- Train Datasets: wannaphong/mark13\n\n\nWe fork EasyLM and added training by HuggingFace datasets, but HuggingFace was down many times during the time we trained the model, so we can train just one epoch. The model trained one epoch.", "# Acknowledgements\n\nResearch supported with Cloud TPUs from Google's TPU Research Cloud (TRC). We use TPU4-64 for training model about 4 days / 1 epoch.\n\nThank you TPU Research Cloud and EasyLM project! We use EasyLM for pretraining model." ]

[ 56, 147, 60 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #en #th #dataset-wannaphong/mark13 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n## NumFaLM 3B\nNumFaLM 3B is a bilingual language model trained in Thai and English. The architecture model is Llama model that pretraining from scratch. It was built to open source AI and research for bilingual language models and improve small language models. We released the training script and train datasets so you can research the training and datasets.\n\n- GitHub: URL\n- Training script: URL\n- Train Datasets: wannaphong/mark13\n\n\nWe fork EasyLM and added training by HuggingFace datasets, but HuggingFace was down many times during the time we trained the model, so we can train just one epoch. The model trained one epoch.# Acknowledgements\n\nResearch supported with Cloud TPUs from Google's TPU Research Cloud (TRC). We use TPU4-64 for training model about 4 days / 1 epoch.\n\nThank you TPU Research Cloud and EasyLM project! We use EasyLM for pretraining model." ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 5000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 5000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 52, 126, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 5000\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "plbart", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #plbart #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 34, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #plbart #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gemma", "text-generation", "license:gemma", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Description\n\n\nCodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.", "### Sample Usage", "#### For Code Completion\n\n\nCode completion can be used for infilling inside code editors. CodeGemma was trained for this task using the fill-in-the-middle (FIM) objective, where you provide a prefix and a suffix as context for the completion. The following tokens are used to separate the different parts of the input:\n\n\n* '<|fim\\_prefix|>' precedes the context before the completion we want to run.\n* '<|fim\\_suffix|>' precedes the suffix. You must put this token exactly where the cursor would be positioned in an editor, as this is the location that will be completed by the model.\n* '<|fim\\_middle|>' is the prompt that invites the model to run the generation.\n\n\nIn addition to these, there's also '<|file\\_separator|>', which is used to provide multi-file contexts.\n\n\nPlease, make sure to not provide any extra spaces or newlines around the tokens, other than those that would naturally occur in the code fragment you want to complete. Here's an example:\n\n\nThis may return something like the following:\n\n\nNote the extra content after the correct completion. The model returns the completion, followed by one of the FIM tokens or the EOS token. You should ignore everything that comes after any of these tokens. A good way to achieve this is by providing a list of terminators to the 'generate' function, like this:\n\n\nIn this case, generation stops as soon as the first delimiter is found in the response:", "#### For Code Generation", "### Inputs and Outputs\n\n\nInputs\n: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt\n: For instruction tuned model variant: natural language text or prompt\n\n\nOutputs\n: For pretrained model variants: fill-in-the-middle code completion, code and natural language\n: For instruction tuned model variant: code and natural language\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nUsing Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.", "### Training Data Processing\n\n\nThe following data pre-processing techniques were applied:\n\n\n* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50-50 PSM/SPM.\n* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing\n* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.\n* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.\n\n\nImplementation Information\n--------------------------\n\n\nInformation about the hardware and software used to train the models.", "### Hardware\n\n\nCodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nEvaluation Information\n----------------------\n\n\nModel evaluation metrics and results.", "### Evaluation Approach\n\n\nWe evaluate CodeGemma on a variety of academic benchmarks across several domains:\n\n\n* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling\n* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)\n* Q&A: BoolQ, PIQA, TriviaQA\n* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande\n* Math Reasoning: GSM8K, MATH", "### Evaluation Results", "#### Coding Benchmarks", "#### Natural Language Benchmarks\n\n\n!CodeGemma Natural Language Benchmarks\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:\n\n\n* Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.\n* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the Gemma model card for more details.\n\n\nModel Usage & Limitations\n-------------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nCode Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.\n\n\nCode Completion\n: PT models can be used to complete code with an IDE extension\n\n\nCode Generation\n: IT model can be used to generate code with or without an IDE extension\n\n\nCode Conversation\n: IT model can power conversation interfaces which discuss code.\n\n\nCode Education\n: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.", "### Known Limitations\n\n\nLarge Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.", "### Ethical Considerations & Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.\n\n\nUsing the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #license-gemma #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Description\n\n\nCodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.", "### Sample Usage", "#### For Code Completion\n\n\nCode completion can be used for infilling inside code editors. CodeGemma was trained for this task using the fill-in-the-middle (FIM) objective, where you provide a prefix and a suffix as context for the completion. The following tokens are used to separate the different parts of the input:\n\n\n* '<|fim\\_prefix|>' precedes the context before the completion we want to run.\n* '<|fim\\_suffix|>' precedes the suffix. You must put this token exactly where the cursor would be positioned in an editor, as this is the location that will be completed by the model.\n* '<|fim\\_middle|>' is the prompt that invites the model to run the generation.\n\n\nIn addition to these, there's also '<|file\\_separator|>', which is used to provide multi-file contexts.\n\n\nPlease, make sure to not provide any extra spaces or newlines around the tokens, other than those that would naturally occur in the code fragment you want to complete. Here's an example:\n\n\nThis may return something like the following:\n\n\nNote the extra content after the correct completion. The model returns the completion, followed by one of the FIM tokens or the EOS token. You should ignore everything that comes after any of these tokens. A good way to achieve this is by providing a list of terminators to the 'generate' function, like this:\n\n\nIn this case, generation stops as soon as the first delimiter is found in the response:", "#### For Code Generation", "### Inputs and Outputs\n\n\nInputs\n: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt\n: For instruction tuned model variant: natural language text or prompt\n\n\nOutputs\n: For pretrained model variants: fill-in-the-middle code completion, code and natural language\n: For instruction tuned model variant: code and natural language\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nUsing Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.", "### Training Data Processing\n\n\nThe following data pre-processing techniques were applied:\n\n\n* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50-50 PSM/SPM.\n* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing\n* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.\n* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.\n\n\nImplementation Information\n--------------------------\n\n\nInformation about the hardware and software used to train the models.", "### Hardware\n\n\nCodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nEvaluation Information\n----------------------\n\n\nModel evaluation metrics and results.", "### Evaluation Approach\n\n\nWe evaluate CodeGemma on a variety of academic benchmarks across several domains:\n\n\n* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling\n* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)\n* Q&A: BoolQ, PIQA, TriviaQA\n* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande\n* Math Reasoning: GSM8K, MATH", "### Evaluation Results", "#### Coding Benchmarks", "#### Natural Language Benchmarks\n\n\n!CodeGemma Natural Language Benchmarks\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:\n\n\n* Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.\n* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the Gemma model card for more details.\n\n\nModel Usage & Limitations\n-------------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nCode Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.\n\n\nCode Completion\n: PT models can be used to complete code with an IDE extension\n\n\nCode Generation\n: IT model can be used to generate code with or without an IDE extension\n\n\nCode Conversation\n: IT model can power conversation interfaces which discuss code.\n\n\nCode Education\n: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.", "### Known Limitations\n\n\nLarge Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.", "### Ethical Considerations & Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.\n\n\nUsing the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives." ]

[ 37, 91, 5, 338, 7, 104, 63, 263, 30, 44, 120, 5, 7, 44, 113, 96, 130, 42, 50, 74 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #license-gemma #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n### Description\n\n\nCodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.### Sample Usage#### For Code Completion\n\n\nCode completion can be used for infilling inside code editors. CodeGemma was trained for this task using the fill-in-the-middle (FIM) objective, where you provide a prefix and a suffix as context for the completion. The following tokens are used to separate the different parts of the input:\n\n\n* '<|fim\\_prefix|>' precedes the context before the completion we want to run.\n* '<|fim\\_suffix|>' precedes the suffix. You must put this token exactly where the cursor would be positioned in an editor, as this is the location that will be completed by the model.\n* '<|fim\\_middle|>' is the prompt that invites the model to run the generation.\n\n\nIn addition to these, there's also '<|file\\_separator|>', which is used to provide multi-file contexts.\n\n\nPlease, make sure to not provide any extra spaces or newlines around the tokens, other than those that would naturally occur in the code fragment you want to complete. Here's an example:\n\n\nThis may return something like the following:\n\n\nNote the extra content after the correct completion. The model returns the completion, followed by one of the FIM tokens or the EOS token. You should ignore everything that comes after any of these tokens. A good way to achieve this is by providing a list of terminators to the 'generate' function, like this:\n\n\nIn this case, generation stops as soon as the first delimiter is found in the response:#### For Code Generation### Inputs and Outputs\n\n\nInputs\n: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt\n: For instruction tuned model variant: natural language text or prompt\n\n\nOutputs\n: For pretrained model variants: fill-in-the-middle code completion, code and natural language\n: For instruction tuned model variant: code and natural language\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.### Training Dataset\n\n\nUsing Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.### Training Data Processing\n\n\nThe following data pre-processing techniques were applied:\n\n\n* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50-50 PSM/SPM.\n* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing\n* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.\n* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.\n\n\nImplementation Information\n--------------------------\n\n\nInformation about the hardware and software used to train the models.### Hardware\n\n\nCodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nEvaluation Information\n----------------------\n\n\nModel evaluation metrics and results.### Evaluation Approach\n\n\nWe evaluate CodeGemma on a variety of academic benchmarks across several domains:\n\n\n* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling\n* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)\n* Q&A: BoolQ, PIQA, TriviaQA\n* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande\n* Math Reasoning: GSM8K, MATH### Evaluation Results#### Coding Benchmarks#### Natural Language Benchmarks\n\n\n!CodeGemma Natural Language Benchmarks\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:\n\n\n* Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.\n* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the Gemma model card for more details.\n\n\nModel Usage & Limitations\n-------------------------\n\n\nThese models have certain limitations that users should be aware of.### Intended Usage\n\n\nCode Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.\n\n\nCode Completion\n: PT models can be used to complete code with an IDE extension\n\n\nCode Generation\n: IT model can be used to generate code with or without an IDE extension\n\n\nCode Conversation\n: IT model can power conversation interfaces which discuss code.\n\n\nCode Education\n: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.### Known Limitations\n\n\nLarge Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.### Ethical Considerations & Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.### Benefits\n\n\nAt the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.\n\n\nUsing the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives." ]

[ "transformers", "safetensors", "gemma", "text-generation", "license:gemma", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Description\n\n\nCodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.", "### Sample Usage\n\n\nThis model is intended to answer questions about code fragments, to generate code from natural language, or to engage in a conversation with the user about programming or technical problems. If you need to use code completion (for example, integrated in an IDE), we recommend you use one of the pre-trained models instead: CodeGemma 7B, or CodeGemma 2B.", "#### For Code Generation", "#### Chat Template\n\n\nThe instruction-tuned models use a chat template that must be adhered to for conversational use.\nThe easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.\n\n\nLet's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:\n\n\nAt this point, the prompt contains the following text:\n\n\nAs you can see, each turn is preceded by a '<start\\_of\\_turn>' delimiter and then the role of the entity\n(either 'user', for content supplied by the user, or 'model' for LLM responses). Turns finish with\nthe '<end\\_of\\_turn>' token.\n\n\nYou can follow this format to build the prompt manually, if you need to do it without the tokenizer's\nchat template.\n\n\nAfter the prompt is ready, generation can be performed like this:", "### Inputs and Outputs\n\n\nInputs\n: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt\n: For instruction tuned model variant: natural language text or prompt\n\n\nOutputs\n: For pretrained model variants: fill-in-the-middle code completion, code and natural language\n: For instruction tuned model variant: code and natural language\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nUsing Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.", "### Training Data Processing\n\n\nThe following data pre-processing techniques were applied:\n\n\n* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50-50 PSM/SPM.\n* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing\n* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.\n* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.\n\n\nImplementation Information\n--------------------------\n\n\nInformation about the hardware and software used to train the models.", "### Hardware\n\n\nCodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nEvaluation Information\n----------------------\n\n\nModel evaluation metrics and results.", "### Evaluation Approach\n\n\nWe evaluate CodeGemma on a variety of academic benchmarks across several domains:\n\n\n* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling\n* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)\n* Q&A: BoolQ, PIQA, TriviaQA\n* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande\n* Math Reasoning: GSM8K, MATH", "### Evaluation Results", "#### Coding Benchmarks", "#### Natural Language Benchmarks\n\n\n!CodeGemma Natural Language Benchmarks\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:\n\n\n* Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.\n* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the Gemma model card for more details.\n\n\nModel Usage & Limitations\n-------------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nCode Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.\n\n\nCode Completion\n: PT models can be used to complete code with an IDE extension\n\n\nCode Generation\n: IT model can be used to generate code with or without an IDE extension\n\n\nCode Conversation\n: IT model can power conversation interfaces which discuss code.\n\n\nCode Education\n: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.", "### Known Limitations\n\n\nLarge Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.", "### Ethical Considerations & Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.\n\n\nUsing the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #license-gemma #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Description\n\n\nCodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.", "### Sample Usage\n\n\nThis model is intended to answer questions about code fragments, to generate code from natural language, or to engage in a conversation with the user about programming or technical problems. If you need to use code completion (for example, integrated in an IDE), we recommend you use one of the pre-trained models instead: CodeGemma 7B, or CodeGemma 2B.", "#### For Code Generation", "#### Chat Template\n\n\nThe instruction-tuned models use a chat template that must be adhered to for conversational use.\nThe easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.\n\n\nLet's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:\n\n\nAt this point, the prompt contains the following text:\n\n\nAs you can see, each turn is preceded by a '<start\\_of\\_turn>' delimiter and then the role of the entity\n(either 'user', for content supplied by the user, or 'model' for LLM responses). Turns finish with\nthe '<end\\_of\\_turn>' token.\n\n\nYou can follow this format to build the prompt manually, if you need to do it without the tokenizer's\nchat template.\n\n\nAfter the prompt is ready, generation can be performed like this:", "### Inputs and Outputs\n\n\nInputs\n: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt\n: For instruction tuned model variant: natural language text or prompt\n\n\nOutputs\n: For pretrained model variants: fill-in-the-middle code completion, code and natural language\n: For instruction tuned model variant: code and natural language\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nUsing Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.", "### Training Data Processing\n\n\nThe following data pre-processing techniques were applied:\n\n\n* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50-50 PSM/SPM.\n* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing\n* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.\n* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.\n\n\nImplementation Information\n--------------------------\n\n\nInformation about the hardware and software used to train the models.", "### Hardware\n\n\nCodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nEvaluation Information\n----------------------\n\n\nModel evaluation metrics and results.", "### Evaluation Approach\n\n\nWe evaluate CodeGemma on a variety of academic benchmarks across several domains:\n\n\n* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling\n* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)\n* Q&A: BoolQ, PIQA, TriviaQA\n* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande\n* Math Reasoning: GSM8K, MATH", "### Evaluation Results", "#### Coding Benchmarks", "#### Natural Language Benchmarks\n\n\n!CodeGemma Natural Language Benchmarks\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:\n\n\n* Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.\n* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the Gemma model card for more details.\n\n\nModel Usage & Limitations\n-------------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nCode Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.\n\n\nCode Completion\n: PT models can be used to complete code with an IDE extension\n\n\nCode Generation\n: IT model can be used to generate code with or without an IDE extension\n\n\nCode Conversation\n: IT model can power conversation interfaces which discuss code.\n\n\nCode Education\n: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.", "### Known Limitations\n\n\nLarge Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.", "### Ethical Considerations & Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.\n\n\nUsing the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives." ]

[ 37, 91, 82, 7, 205, 104, 63, 263, 30, 44, 120, 5, 7, 44, 113, 96, 130, 42, 50, 74 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #license-gemma #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n### Description\n\n\nCodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.### Sample Usage\n\n\nThis model is intended to answer questions about code fragments, to generate code from natural language, or to engage in a conversation with the user about programming or technical problems. If you need to use code completion (for example, integrated in an IDE), we recommend you use one of the pre-trained models instead: CodeGemma 7B, or CodeGemma 2B.#### For Code Generation#### Chat Template\n\n\nThe instruction-tuned models use a chat template that must be adhered to for conversational use.\nThe easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.\n\n\nLet's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:\n\n\nAt this point, the prompt contains the following text:\n\n\nAs you can see, each turn is preceded by a '<start\\_of\\_turn>' delimiter and then the role of the entity\n(either 'user', for content supplied by the user, or 'model' for LLM responses). Turns finish with\nthe '<end\\_of\\_turn>' token.\n\n\nYou can follow this format to build the prompt manually, if you need to do it without the tokenizer's\nchat template.\n\n\nAfter the prompt is ready, generation can be performed like this:### Inputs and Outputs\n\n\nInputs\n: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt\n: For instruction tuned model variant: natural language text or prompt\n\n\nOutputs\n: For pretrained model variants: fill-in-the-middle code completion, code and natural language\n: For instruction tuned model variant: code and natural language\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.### Training Dataset\n\n\nUsing Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 to 1000 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.### Training Data Processing\n\n\nThe following data pre-processing techniques were applied:\n\n\n* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% to 90% FIM rate with 50-50 PSM/SPM.\n* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing\n* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.\n* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with our policies.\n\n\nImplementation Information\n--------------------------\n\n\nInformation about the hardware and software used to train the models.### Hardware\n\n\nCodeGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e).### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nEvaluation Information\n----------------------\n\n\nModel evaluation metrics and results.### Evaluation Approach\n\n\nWe evaluate CodeGemma on a variety of academic benchmarks across several domains:\n\n\n* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling\n* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)\n* Q&A: BoolQ, PIQA, TriviaQA\n* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande\n* Math Reasoning: GSM8K, MATH### Evaluation Results#### Coding Benchmarks#### Natural Language Benchmarks\n\n\n!CodeGemma Natural Language Benchmarks\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:\n\n\n* Human evaluation on prompts covering content safety and representational harms. See the Gemma model card for more details on evaluation approach.\n* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds for meeting internal policies for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the Gemma model card for more details.\n\n\nModel Usage & Limitations\n-------------------------\n\n\nThese models have certain limitations that users should be aware of.### Intended Usage\n\n\nCode Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.\n\n\nCode Completion\n: PT models can be used to complete code with an IDE extension\n\n\nCode Generation\n: IT model can be used to generate code with or without an IDE extension\n\n\nCode Conversation\n: IT model can power conversation interfaces which discuss code.\n\n\nCode Education\n: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.### Known Limitations\n\n\nLarge Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the Gemma model card for more details on the limitations of LLMs.### Ethical Considerations & Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to the same discussion in the Gemma model card for model details.### Benefits\n\n\nAt the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.\n\n\nUsing the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives." ]

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ 37, 81, 76, 10, 6, 3 ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:## Training (with the RL Zoo)## Hyperparameters# Environment Arguments" ]

[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# vit-base-patch16-224-finetuned-flower\n\nThis model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- Transformers 4.24.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.7.1\n- Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #vit #image-classification #generated_from_trainer #dataset-imagefolder #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# vit-base-patch16-224-finetuned-flower\n\nThis model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- Transformers 4.24.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.7.1\n- Tokenizers 0.13.3" ]

[ 50, 44, 7, 9, 9, 4, 93, 5, 44 ]

[ "TAGS\n#transformers #pytorch #vit #image-classification #generated_from_trainer #dataset-imagefolder #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# vit-base-patch16-224-finetuned-flower\n\nThis model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5### Training results### Framework versions\n\n- Transformers 4.24.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.7.1\n- Tokenizers 0.13.3" ]

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "text-generation", "en", "dataset:yahma/alpaca-cleaned", "license:mit", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Model Card for Model ID\n\nFine-Tuned version of Phi-3-mini", "## Model Details", "### Model Description\n\nQLORA-Fine Tuned version of Phi-3-mini-128k-instruct on the Alpaca dataset\n\n\n- Developed by: Microsoft, Fine-Tuning done by Yours Truly", "### Model Sources [optional]\n\n\n\n- Repository: URL\n- Paper : URL" ]

[ "TAGS\n#transformers #safetensors #text-generation #en #dataset-yahma/alpaca-cleaned #license-mit #endpoints_compatible #region-us \n", "# Model Card for Model ID\n\nFine-Tuned version of Phi-3-mini", "## Model Details", "### Model Description\n\nQLORA-Fine Tuned version of Phi-3-mini-128k-instruct on the Alpaca dataset\n\n\n- Developed by: Microsoft, Fine-Tuning done by Yours Truly", "### Model Sources [optional]\n\n\n\n- Repository: URL\n- Paper : URL" ]

[ 38, 16, 4, 44, 18 ]

[ "TAGS\n#transformers #safetensors #text-generation #en #dataset-yahma/alpaca-cleaned #license-mit #endpoints_compatible #region-us \n# Model Card for Model ID\n\nFine-Tuned version of Phi-3-mini## Model Details### Model Description\n\nQLORA-Fine Tuned version of Phi-3-mini-128k-instruct on the Alpaca dataset\n\n\n- Developed by: Microsoft, Fine-Tuning done by Yours Truly### Model Sources [optional]\n\n\n\n- Repository: URL\n- Paper : URL" ]

[ "license:openrail", "region:us" ]

[]

[]

[ "# DETAILS\n\n - Trained with 40 hours of raw data I can add more data in the future\n\n (Ariana grande, Dua lipa , Charlie Puth, Joji, Freddie Mercury, Michael Jackson)\n - Fine Tuned with ov2 pretrain\n - 32k still training 5 EPOCHS\n - 40k maybe I'll train it\n - 48k MAYBE I'll train it" ]

[ "TAGS\n#license-openrail #region-us \n", "# DETAILS\n\n - Trained with 40 hours of raw data I can add more data in the future\n\n (Ariana grande, Dua lipa , Charlie Puth, Joji, Freddie Mercury, Michael Jackson)\n - Fine Tuned with ov2 pretrain\n - 32k still training 5 EPOCHS\n - 40k maybe I'll train it\n - 48k MAYBE I'll train it" ]

[ 10, 76 ]

[ "TAGS\n#license-openrail #region-us \n# DETAILS\n\n - Trained with 40 hours of raw data I can add more data in the future\n\n (Ariana grande, Dua lipa , Charlie Puth, Joji, Freddie Mercury, Michael Jackson)\n - Fine Tuned with ov2 pretrain\n - 32k still training 5 EPOCHS\n - 40k maybe I'll train it\n - 48k MAYBE I'll train it" ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[]

[ "# Perfect World 完美世界 v6 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"perfect-world-v6\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"perfect-world-v6\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# Perfect World 完美世界 v6 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"perfect-world-v6\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"perfect-world-v6\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ 54, 15, 511 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n# Perfect World 完美世界 v6 API Inference\n\n!generated from URL## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"perfect-world-v6\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"perfect-world-v6\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 22, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "endpoints_compatible", "region:us" ]

[]

[]

[ "# jayrodge/Llama3-3-8B-Instruct-ft-loraAdap-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'patelmiteshn/Llama3-3-8B-Instruct-ft-loraAdap' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#transformers #gguf #llama-cpp #gguf-my-repo #endpoints_compatible #region-us \n", "# jayrodge/Llama3-3-8B-Instruct-ft-loraAdap-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'patelmiteshn/Llama3-3-8B-Instruct-ft-loraAdap' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 31, 101, 52 ]

[ "TAGS\n#transformers #gguf #llama-cpp #gguf-my-repo #endpoints_compatible #region-us \n# jayrodge/Llama3-3-8B-Instruct-ft-loraAdap-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'patelmiteshn/Llama3-3-8B-Instruct-ft-loraAdap' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "pytorch", "tflite", "android", "image-segmentation", "dataset:VOC2012", "arxiv:1706.05587", "license:mit", "region:us" ]

[ "1706.05587" ]

[]

[ "### Model Details\n\n\n* Model Type: Semantic segmentation\n* Model Stats:\n\t+ Model checkpoint: VOC2012\n\t+ Input resolution: 513x513\n\t+ Number of parameters: 5.80M\n\t+ Model size: 22.2 MB\n\n\n\nInstallation\n------------\n\n\nThis model can be installed as a Python package via pip.\n\n\nConfigure Qualcomm® AI Hub to run this model on a cloud-hosted device\n---------------------------------------------------------------------\n\n\nSign-in to Qualcomm® AI Hub with your\nQualcomm® ID. Once signed in navigate to 'Account -> Settings -> API Token'.\n\n\nWith this API token, you can configure your client to run models on the cloud\nhosted devices.\n\n\nNavigate to docs for more information.\n\n\nDemo off target\n---------------\n\n\nThe package contains a simple end-to-end demo that downloads pre-trained\nweights and runs this model on a sample input.\n\n\nThe above demo runs a reference implementation of pre-processing, model\ninference, and post processing.\n\n\nNOTE: If you want running in a Jupyter Notebook or Google Colab like\nenvironment, please add the following to your cell (instead of the above).", "### Run model on a cloud-hosted device\n\n\nIn addition to the demo, you can also run the model on a cloud-hosted Qualcomm®\ndevice. This script does the following:\n\n\n* Performance check on-device on a cloud-hosted device\n* Downloads compiled assets that can be deployed on-device for Android.\n* Accuracy check between PyTorch and on-device outputs.\n\n\nHow does this work?\n-------------------\n\n\nThis export script\nleverages Qualcomm® AI Hub to optimize, validate, and deploy this model\non-device. Lets go through each step below in detail:\n\n\nStep 1: Compile model for on-device deployment\n\n\nTo compile a PyTorch model for on-device deployment, we first trace the model\nin memory using the 'URL' and then call the 'submit\\_compile\\_job' API.\n\n\nStep 2: Performance profiling on cloud-hosted device\n\n\nAfter compiling models from step 1. Models can be profiled model on-device using the\n'target\\_model'. Note that this scripts runs the model on a device automatically\nprovisioned in the cloud. Once the job is submitted, you can navigate to a\nprovided job URL to view a variety of on-device performance metrics.\n\n\nStep 3: Verify on-device accuracy\n\n\nTo verify the accuracy of the model on-device, you can run on-device inference\non sample input data on the same cloud hosted device.\n\n\nWith the output of the model, you can compute like PSNR, relative errors or\nspot check the output with expected output.\n\n\nNote: This on-device profiling and inference requires access to Qualcomm®\nAI Hub. Sign up for access.\n\n\nRun demo on a cloud-hosted device\n---------------------------------\n\n\nYou can also run the demo on-device.\n\n\nNOTE: If you want running in a Jupyter Notebook or Google Colab like\nenvironment, please add the following to your cell (instead of the above).\n\n\nDeploying compiled model to Android\n-----------------------------------\n\n\nThe models can be deployed using multiple runtimes:\n\n\n* TensorFlow Lite ('.tflite' export): This\ntutorial provides a\nguide to deploy the .tflite model in an Android application.\n* QNN ('.so' export ): This sample\napp\nprovides instructions on how to use the '.so' shared library in an Android application.\n\n\nView on Qualcomm® AI Hub\n------------------------\n\n\nGet more details on DeepLabV3-Plus-MobileNet's performance across various devices here.\nExplore all available models on Qualcomm® AI Hub\n\n\nLicense\n-------\n\n\n* The license for the original implementation of DeepLabV3-Plus-MobileNet can be found\nhere.\n* The license for the compiled assets for on-device deployment can be found here\n\n\nReferences\n----------\n\n\n* Rethinking Atrous Convolution for Semantic Image Segmentation\n* Source Model Implementation\n\n\nCommunity\n---------\n\n\n* Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.\n* For questions or feedback please reach out to us." ]

[ "TAGS\n#pytorch #tflite #android #image-segmentation #dataset-VOC2012 #arxiv-1706.05587 #license-mit #region-us \n", "### Model Details\n\n\n* Model Type: Semantic segmentation\n* Model Stats:\n\t+ Model checkpoint: VOC2012\n\t+ Input resolution: 513x513\n\t+ Number of parameters: 5.80M\n\t+ Model size: 22.2 MB\n\n\n\nInstallation\n------------\n\n\nThis model can be installed as a Python package via pip.\n\n\nConfigure Qualcomm® AI Hub to run this model on a cloud-hosted device\n---------------------------------------------------------------------\n\n\nSign-in to Qualcomm® AI Hub with your\nQualcomm® ID. Once signed in navigate to 'Account -> Settings -> API Token'.\n\n\nWith this API token, you can configure your client to run models on the cloud\nhosted devices.\n\n\nNavigate to docs for more information.\n\n\nDemo off target\n---------------\n\n\nThe package contains a simple end-to-end demo that downloads pre-trained\nweights and runs this model on a sample input.\n\n\nThe above demo runs a reference implementation of pre-processing, model\ninference, and post processing.\n\n\nNOTE: If you want running in a Jupyter Notebook or Google Colab like\nenvironment, please add the following to your cell (instead of the above).", "### Run model on a cloud-hosted device\n\n\nIn addition to the demo, you can also run the model on a cloud-hosted Qualcomm®\ndevice. This script does the following:\n\n\n* Performance check on-device on a cloud-hosted device\n* Downloads compiled assets that can be deployed on-device for Android.\n* Accuracy check between PyTorch and on-device outputs.\n\n\nHow does this work?\n-------------------\n\n\nThis export script\nleverages Qualcomm® AI Hub to optimize, validate, and deploy this model\non-device. Lets go through each step below in detail:\n\n\nStep 1: Compile model for on-device deployment\n\n\nTo compile a PyTorch model for on-device deployment, we first trace the model\nin memory using the 'URL' and then call the 'submit\\_compile\\_job' API.\n\n\nStep 2: Performance profiling on cloud-hosted device\n\n\nAfter compiling models from step 1. Models can be profiled model on-device using the\n'target\\_model'. Note that this scripts runs the model on a device automatically\nprovisioned in the cloud. Once the job is submitted, you can navigate to a\nprovided job URL to view a variety of on-device performance metrics.\n\n\nStep 3: Verify on-device accuracy\n\n\nTo verify the accuracy of the model on-device, you can run on-device inference\non sample input data on the same cloud hosted device.\n\n\nWith the output of the model, you can compute like PSNR, relative errors or\nspot check the output with expected output.\n\n\nNote: This on-device profiling and inference requires access to Qualcomm®\nAI Hub. Sign up for access.\n\n\nRun demo on a cloud-hosted device\n---------------------------------\n\n\nYou can also run the demo on-device.\n\n\nNOTE: If you want running in a Jupyter Notebook or Google Colab like\nenvironment, please add the following to your cell (instead of the above).\n\n\nDeploying compiled model to Android\n-----------------------------------\n\n\nThe models can be deployed using multiple runtimes:\n\n\n* TensorFlow Lite ('.tflite' export): This\ntutorial provides a\nguide to deploy the .tflite model in an Android application.\n* QNN ('.so' export ): This sample\napp\nprovides instructions on how to use the '.so' shared library in an Android application.\n\n\nView on Qualcomm® AI Hub\n------------------------\n\n\nGet more details on DeepLabV3-Plus-MobileNet's performance across various devices here.\nExplore all available models on Qualcomm® AI Hub\n\n\nLicense\n-------\n\n\n* The license for the original implementation of DeepLabV3-Plus-MobileNet can be found\nhere.\n* The license for the compiled assets for on-device deployment can be found here\n\n\nReferences\n----------\n\n\n* Rethinking Atrous Convolution for Semantic Image Segmentation\n* Source Model Implementation\n\n\nCommunity\n---------\n\n\n* Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.\n* For questions or feedback please reach out to us." ]

[ 44, 327, 752 ]

[ "TAGS\n#pytorch #tflite #android #image-segmentation #dataset-VOC2012 #arxiv-1706.05587 #license-mit #region-us \n### Model Details\n\n\n* Model Type: Semantic segmentation\n* Model Stats:\n\t+ Model checkpoint: VOC2012\n\t+ Input resolution: 513x513\n\t+ Number of parameters: 5.80M\n\t+ Model size: 22.2 MB\n\n\n\nInstallation\n------------\n\n\nThis model can be installed as a Python package via pip.\n\n\nConfigure Qualcomm® AI Hub to run this model on a cloud-hosted device\n---------------------------------------------------------------------\n\n\nSign-in to Qualcomm® AI Hub with your\nQualcomm® ID. Once signed in navigate to 'Account -> Settings -> API Token'.\n\n\nWith this API token, you can configure your client to run models on the cloud\nhosted devices.\n\n\nNavigate to docs for more information.\n\n\nDemo off target\n---------------\n\n\nThe package contains a simple end-to-end demo that downloads pre-trained\nweights and runs this model on a sample input.\n\n\nThe above demo runs a reference implementation of pre-processing, model\ninference, and post processing.\n\n\nNOTE: If you want running in a Jupyter Notebook or Google Colab like\nenvironment, please add the following to your cell (instead of the above).### Run model on a cloud-hosted device\n\n\nIn addition to the demo, you can also run the model on a cloud-hosted Qualcomm®\ndevice. This script does the following:\n\n\n* Performance check on-device on a cloud-hosted device\n* Downloads compiled assets that can be deployed on-device for Android.\n* Accuracy check between PyTorch and on-device outputs.\n\n\nHow does this work?\n-------------------\n\n\nThis export script\nleverages Qualcomm® AI Hub to optimize, validate, and deploy this model\non-device. Lets go through each step below in detail:\n\n\nStep 1: Compile model for on-device deployment\n\n\nTo compile a PyTorch model for on-device deployment, we first trace the model\nin memory using the 'URL' and then call the 'submit\\_compile\\_job' API.\n\n\nStep 2: Performance profiling on cloud-hosted device\n\n\nAfter compiling models from step 1. Models can be profiled model on-device using the\n'target\\_model'. Note that this scripts runs the model on a device automatically\nprovisioned in the cloud. Once the job is submitted, you can navigate to a\nprovided job URL to view a variety of on-device performance metrics.\n\n\nStep 3: Verify on-device accuracy\n\n\nTo verify the accuracy of the model on-device, you can run on-device inference\non sample input data on the same cloud hosted device.\n\n\nWith the output of the model, you can compute like PSNR, relative errors or\nspot check the output with expected output.\n\n\nNote: This on-device profiling and inference requires access to Qualcomm®\nAI Hub. Sign up for access.\n\n\nRun demo on a cloud-hosted device\n---------------------------------\n\n\nYou can also run the demo on-device.\n\n\nNOTE: If you want running in a Jupyter Notebook or Google Colab like\nenvironment, please add the following to your cell (instead of the above).\n\n\nDeploying compiled model to Android\n-----------------------------------\n\n\nThe models can be deployed using multiple runtimes:\n\n\n* TensorFlow Lite ('.tflite' export): This\ntutorial provides a\nguide to deploy the .tflite model in an Android application.\n* QNN ('.so' export ): This sample\napp\nprovides instructions on how to use the '.so' shared library in an Android application.\n\n\nView on Qualcomm® AI Hub\n------------------------\n\n\nGet more details on DeepLabV3-Plus-MobileNet's performance across various devices here.\nExplore all available models on Qualcomm® AI Hub\n\n\nLicense\n-------\n\n\n* The license for the original implementation of DeepLabV3-Plus-MobileNet can be found\nhere.\n* The license for the compiled assets for on-device deployment can be found here\n\n\nReferences\n----------\n\n\n* Rethinking Atrous Convolution for Semantic Image Segmentation\n* Source Model Implementation\n\n\nCommunity\n---------\n\n\n* Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.\n* For questions or feedback please reach out to us." ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 39, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "gguf", "region:us" ]

[]

[]

[ "# LocAlM\n\nCompact yet powerful, LocAlM efficiently identifies the appropriate medical specialists based on your specific needs and preferences. (Less than 25 tokens per prompt!!!)\n\n<img src=\"URL width=400 />\n\n> Alm is a small but smart duck, reminiscent in size of his parent model, phi3", "# Versions\n\nLocAlM comes in 2 versions.\n\nI recommand you use the latest version: *URL*\n\nYou can load the model in Ollama if you want to run it locally. The model is very small and takes only 2.5G.\n\nIn order to use *URL*, follow this alpaca prompt format:" ]

[ "TAGS\n#gguf #region-us \n", "# LocAlM\n\nCompact yet powerful, LocAlM efficiently identifies the appropriate medical specialists based on your specific needs and preferences. (Less than 25 tokens per prompt!!!)\n\n<img src=\"URL width=400 />\n\n> Alm is a small but smart duck, reminiscent in size of his parent model, phi3", "# Versions\n\nLocAlM comes in 2 versions.\n\nI recommand you use the latest version: *URL*\n\nYou can load the model in Ollama if you want to run it locally. The model is very small and takes only 2.5G.\n\nIn order to use *URL*, follow this alpaca prompt format:" ]

[ 9, 69, 71 ]

[ "TAGS\n#gguf #region-us \n# LocAlM\n\nCompact yet powerful, LocAlM efficiently identifies the appropriate medical specialists based on your specific needs and preferences. (Less than 25 tokens per prompt!!!)\n\n<img src=\"URL width=400 />\n\n> Alm is a small but smart duck, reminiscent in size of his parent model, phi3# Versions\n\nLocAlM comes in 2 versions.\n\nI recommand you use the latest version: *URL*\n\nYou can load the model in Ollama if you want to run it locally. The model is very small and takes only 2.5G.\n\nIn order to use *URL*, follow this alpaca prompt format:" ]

[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Card for Model ID\n\nPhi3-mini-128k and phi3-mini-alpaca merged" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID\n\nPhi3-mini-128k and phi3-mini-alpaca merged" ]

[ 35, 23 ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID\n\nPhi3-mini-128k and phi3-mini-alpaca merged" ]

[ "tensorboard", "license:mit", "region:us" ]

[]

[]

[ "# RVC Voice Model", "## Overview\nThis repository contains the RVC Voice Model, a robust machine learning model for voice synthesis. The model is designed to accurately replicate a specific voice, providing high-quality audio output suitable for various applications.", "## File Structure\n- Index File: 'logs/dotcom/added_IVF8_Flat_nprobe_1_dotcom_v2.index'\n - This index file is crucial for the operation of the model, facilitating efficient data retrieval.\n- Model File: 'logs/dotcom/D_2333333.pth'\n - Contains the model parameters necessary for voice synthesis.\n- Weights File: 'weights/URL'\n - Stores the trained weights of the model, essential for generating the target voice.", "## Usage\nThe RVC Voice Model is fully unrestricted for any type of use, provided that proper credit is given to the creator. You are free to integrate, modify, and distribute this model in both personal and commercial projects.", "## Credit\nIf you use this model, please credit as follows:\n- Creator of RVC model: URL", "## Disclaimer\nThe individual(voice source) on whom this voice model is based has been involved in activities considered highly illegal. The creation of this model is for educational and research purposes only, and it should not be used to glorify or endorse any illegal activities.", "## License\nThis project is licensed under the terms of the MIT License.", "## Contact\nIf you have any questions or need further information, please feel free to reach out via admin@URL.\n\nThank you for using or contributing to the RVC Voice Model project!" ]

[ "TAGS\n#tensorboard #license-mit #region-us \n", "# RVC Voice Model", "## Overview\nThis repository contains the RVC Voice Model, a robust machine learning model for voice synthesis. The model is designed to accurately replicate a specific voice, providing high-quality audio output suitable for various applications.", "## File Structure\n- Index File: 'logs/dotcom/added_IVF8_Flat_nprobe_1_dotcom_v2.index'\n - This index file is crucial for the operation of the model, facilitating efficient data retrieval.\n- Model File: 'logs/dotcom/D_2333333.pth'\n - Contains the model parameters necessary for voice synthesis.\n- Weights File: 'weights/URL'\n - Stores the trained weights of the model, essential for generating the target voice.", "## Usage\nThe RVC Voice Model is fully unrestricted for any type of use, provided that proper credit is given to the creator. You are free to integrate, modify, and distribute this model in both personal and commercial projects.", "## Credit\nIf you use this model, please credit as follows:\n- Creator of RVC model: URL", "## Disclaimer\nThe individual(voice source) on whom this voice model is based has been involved in activities considered highly illegal. The creation of this model is for educational and research purposes only, and it should not be used to glorify or endorse any illegal activities.", "## License\nThis project is licensed under the terms of the MIT License.", "## Contact\nIf you have any questions or need further information, please feel free to reach out via admin@URL.\n\nThank you for using or contributing to the RVC Voice Model project!" ]

[ 12, 5, 43, 108, 47, 23, 58, 15, 40 ]

[ "TAGS\n#tensorboard #license-mit #region-us \n# RVC Voice Model## Overview\nThis repository contains the RVC Voice Model, a robust machine learning model for voice synthesis. The model is designed to accurately replicate a specific voice, providing high-quality audio output suitable for various applications.## File Structure\n- Index File: 'logs/dotcom/added_IVF8_Flat_nprobe_1_dotcom_v2.index'\n - This index file is crucial for the operation of the model, facilitating efficient data retrieval.\n- Model File: 'logs/dotcom/D_2333333.pth'\n - Contains the model parameters necessary for voice synthesis.\n- Weights File: 'weights/URL'\n - Stores the trained weights of the model, essential for generating the target voice.## Usage\nThe RVC Voice Model is fully unrestricted for any type of use, provided that proper credit is given to the creator. You are free to integrate, modify, and distribute this model in both personal and commercial projects.## Credit\nIf you use this model, please credit as follows:\n- Creator of RVC model: URL## Disclaimer\nThe individual(voice source) on whom this voice model is based has been involved in activities considered highly illegal. The creation of this model is for educational and research purposes only, and it should not be used to glorify or endorse any illegal activities.## License\nThis project is licensed under the terms of the MIT License.## Contact\nIf you have any questions or need further information, please feel free to reach out via admin@URL.\n\nThank you for using or contributing to the RVC Voice Model project!" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: katharsis\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: katharsis\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 76, 80 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: katharsis\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "autotrain", "dataset:v11/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Trained Using AutoTrain\n\n- Problem type: Text Classification", "## Validation Metrics\nloss: 0.4699208438396454\n\nf1_macro: 0.8648394526320947\n\nf1_micro: 0.8277777777777777\n\nf1_weighted: 0.827145991318232\n\nprecision_macro: 0.8595340501792115\n\nprecision_micro: 0.8277777777777777\n\nprecision_weighted: 0.8456027479091995\n\nrecall_macro: 0.8846808510638299\n\nrecall_micro: 0.8277777777777777\n\nrecall_weighted: 0.8277777777777777\n\naccuracy: 0.8277777777777777" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #dataset-v11/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\n- Problem type: Text Classification", "## Validation Metrics\nloss: 0.4699208438396454\n\nf1_macro: 0.8648394526320947\n\nf1_micro: 0.8277777777777777\n\nf1_weighted: 0.827145991318232\n\nprecision_macro: 0.8595340501792115\n\nprecision_micro: 0.8277777777777777\n\nprecision_weighted: 0.8456027479091995\n\nrecall_macro: 0.8846808510638299\n\nrecall_micro: 0.8277777777777777\n\nrecall_weighted: 0.8277777777777777\n\naccuracy: 0.8277777777777777" ]

[ 44, 12, 198 ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #dataset-v11/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n# Model Trained Using AutoTrain\n\n- Problem type: Text Classification## Validation Metrics\nloss: 0.4699208438396454\n\nf1_macro: 0.8648394526320947\n\nf1_micro: 0.8277777777777777\n\nf1_weighted: 0.827145991318232\n\nprecision_macro: 0.8595340501792115\n\nprecision_micro: 0.8277777777777777\n\nprecision_weighted: 0.8456027479091995\n\nrecall_macro: 0.8846808510638299\n\nrecall_micro: 0.8277777777777777\n\nrecall_weighted: 0.8277777777777777\n\naccuracy: 0.8277777777777777" ]

[ "llama.cpp", "gguf", "text-generation", "license:gemma", "region:us" ]

[]

[]

[]

[ "TAGS\n#llama.cpp #gguf #text-generation #license-gemma #region-us \n" ]

[ 23 ]

[ "TAGS\n#llama.cpp #gguf #text-generation #license-gemma #region-us \n" ]

[ "llama.cpp", "gguf", "text-generation", "license:gemma", "region:us" ]

[]

[]

[]

[ "TAGS\n#llama.cpp #gguf #text-generation #license-gemma #region-us \n" ]

[ 23 ]

[ "TAGS\n#llama.cpp #gguf #text-generation #license-gemma #region-us \n" ]

[ "gguf", "merge", "llama-cpp", "gguf-my-repo", "license:apache-2.0", "region:us" ]

[]

[]

[ "# cleatherbury/CatPPT-base-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'rishiraj/CatPPT-base' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n", "# cleatherbury/CatPPT-base-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'rishiraj/CatPPT-base' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 34, 75, 52 ]

[ "TAGS\n#gguf #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n# cleatherbury/CatPPT-base-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'rishiraj/CatPPT-base' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]

[]

[]

[ "# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: dhajnes/ppo-SnowballTarget\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SnowballTarget #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SnowballTarget #region-us \n", "# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: dhajnes/ppo-SnowballTarget\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ 39, 205 ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SnowballTarget #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SnowballTarget #region-us \n# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: dhajnes/ppo-SnowballTarget\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: katharsis\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: katharsis\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 64, 80 ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: katharsis\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "gemma_torch", "pytorch", "text-generation", "license:gemma", "region:us" ]

[]

[]

[ "# CodeGemma Model Card\n\n> [!IMPORTANT]\n>\n> This repository corresponds to the CodeGemma 7B IT checkpoint for use with Gemma PyTorch. If you're looking for the 'transformers' implementation, or more detailed model card, visit URL\n\nModel Page: CodeGemma\n\nResources and Technical Documentation:\n\n* Technical Report\n* Responsible Generative AI Toolkit\n\nTerms of Use: Terms\n\nAuthors: Google", "# Sample Usage" ]

[ "TAGS\n#gemma_torch #pytorch #text-generation #license-gemma #region-us \n", "# CodeGemma Model Card\n\n> [!IMPORTANT]\n>\n> This repository corresponds to the CodeGemma 7B IT checkpoint for use with Gemma PyTorch. If you're looking for the 'transformers' implementation, or more detailed model card, visit URL\n\nModel Page: CodeGemma\n\nResources and Technical Documentation:\n\n* Technical Report\n* Responsible Generative AI Toolkit\n\nTerms of Use: Terms\n\nAuthors: Google", "# Sample Usage" ]

[ 22, 84, 3 ]

[ "TAGS\n#gemma_torch #pytorch #text-generation #license-gemma #region-us \n# CodeGemma Model Card\n\n> [!IMPORTANT]\n>\n> This repository corresponds to the CodeGemma 7B IT checkpoint for use with Gemma PyTorch. If you're looking for the 'transformers' implementation, or more detailed model card, visit URL\n\nModel Page: CodeGemma\n\nResources and Technical Documentation:\n\n* Technical Report\n* Responsible Generative AI Toolkit\n\nTerms of Use: Terms\n\nAuthors: Google# Sample Usage" ]

[ "gemma_torch", "pytorch", "text-generation", "license:gemma", "region:us" ]

[]

[]

[ "# CodeGemma Model Card\n\n> [!IMPORTANT]\n>\n> This repository corresponds to the CodeGemma 2B checkpoint for use with Gemma PyTorch. If you're looking for the 'transformers' implementation, or more detailed model card, visit URL\n\nModel Page: CodeGemma\n\nResources and Technical Documentation:\n\n* Technical Report\n* Responsible Generative AI Toolkit\n\nTerms of Use: Terms\n\nAuthors: Google", "# Sample Usage" ]

[ "TAGS\n#gemma_torch #pytorch #text-generation #license-gemma #region-us \n", "# CodeGemma Model Card\n\n> [!IMPORTANT]\n>\n> This repository corresponds to the CodeGemma 2B checkpoint for use with Gemma PyTorch. If you're looking for the 'transformers' implementation, or more detailed model card, visit URL\n\nModel Page: CodeGemma\n\nResources and Technical Documentation:\n\n* Technical Report\n* Responsible Generative AI Toolkit\n\nTerms of Use: Terms\n\nAuthors: Google", "# Sample Usage" ]

[ 22, 83, 3 ]

[ "TAGS\n#gemma_torch #pytorch #text-generation #license-gemma #region-us \n# CodeGemma Model Card\n\n> [!IMPORTANT]\n>\n> This repository corresponds to the CodeGemma 2B checkpoint for use with Gemma PyTorch. If you're looking for the 'transformers' implementation, or more detailed model card, visit URL\n\nModel Page: CodeGemma\n\nResources and Technical Documentation:\n\n* Technical Report\n* Responsible Generative AI Toolkit\n\nTerms of Use: Terms\n\nAuthors: Google# Sample Usage" ]

[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "autotrain", "text-regression", "dataset:autotrain-y5fnj-qjq2l/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Trained Using AutoTrain\n\n- Problem type: Text Regression", "## Validation Metrics\nloss: 0.19687849283218384\n\nmse: 0.19687849283218384\n\nmae: 0.2855921685695648\n\nr2: 0.2613240842619654\n\nrmse: 0.4437099099159241\n\nexplained_variance: 0.26253634691238403" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #text-regression #dataset-autotrain-y5fnj-qjq2l/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\n- Problem type: Text Regression", "## Validation Metrics\nloss: 0.19687849283218384\n\nmse: 0.19687849283218384\n\nmae: 0.2855921685695648\n\nr2: 0.2613240842619654\n\nrmse: 0.4437099099159241\n\nexplained_variance: 0.26253634691238403" ]

[ 60, 12, 91 ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #text-regression #dataset-autotrain-y5fnj-qjq2l/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n# Model Trained Using AutoTrain\n\n- Problem type: Text Regression## Validation Metrics\nloss: 0.19687849283218384\n\nmse: 0.19687849283218384\n\nmae: 0.2855921685695648\n\nr2: 0.2613240842619654\n\nrmse: 0.4437099099159241\n\nexplained_variance: 0.26253634691238403" ]

[ "safetensors", "license:other", "region:us" ]

[]

[]

[]

[ "TAGS\n#safetensors #license-other #region-us \n" ]

[ 13 ]

[ "TAGS\n#safetensors #license-other #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "orpo", "en", "base_model:jtatman/OrpoDolphin-3-8B-16k", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #orpo #en #base_model-jtatman/OrpoDolphin-3-8B-16k #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ 67 ]

[ "TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #orpo #en #base_model-jtatman/OrpoDolphin-3-8B-16k #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "mt5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #mt5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 46, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #mt5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "spacy", "token-classification", "en", "region:us" ]

[]

[ "en" ]

[ "### Label Scheme\n\n\n\nView label scheme (9 labels for 1 components)" ]

[ "TAGS\n#spacy #token-classification #en #region-us \n", "### Label Scheme\n\n\n\nView label scheme (9 labels for 1 components)" ]

[ 14, 15 ]

[ "TAGS\n#spacy #token-classification #en #region-us \n### Label Scheme\n\n\n\nView label scheme (9 labels for 1 components)" ]

[ "gguf", "llava", "llama", "llava-llama", "GGUF", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #llava #llama #llava-llama #GGUF #region-us \n" ]

[ 25 ]

[ "TAGS\n#gguf #llava #llama #llava-llama #GGUF #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-tiny.en", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.1.dev0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-tiny.en #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.1.dev0\n* Tokenizers 0.19.1" ]

[ 54, 115, 5, 47 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-tiny.en #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.1.dev0\n* Tokenizers 0.19.1" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

[]

[]

[ "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"9527-detail-realistic-xl\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"9527-detail-realistic-xl\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"9527-detail-realistic-xl\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"9527-detail-realistic-xl\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ 56, 8, 517 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n# API Inference\n\n!generated from URL## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"9527-detail-realistic-xl\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"9527-detail-realistic-xl\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Qwen1.5-32B", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:\n\n* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in Chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Usage\n\nWe do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Qwen1.5-32B", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:\n\n* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in Chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Usage\n\nWe do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ 42, 9, 160, 119, 44, 66 ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Qwen1.5-32B## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:\n\n* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in Chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:## Usage\n\nWe do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "plbart", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #plbart #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 34, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #plbart #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "gguf", "en", "base_model:namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged", "license:mit", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged #license-mit #endpoints_compatible #region-us \n" ]

[ 51 ]

[ "TAGS\n#transformers #gguf #en #base_model-namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged #license-mit #endpoints_compatible #region-us \n" ]

[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - embracellm/sushi09_LoRA\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi09_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Salmon Sushi Burrito to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #dora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - embracellm/sushi09_LoRA\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi09_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Salmon Sushi Burrito to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ 72, 25, 85, 21, 25, 6, 7, 23, 17 ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #dora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - embracellm/sushi09_LoRA\n\n<Gallery />## Model description\n\nThese are embracellm/sushi09_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.## Trigger words\n\nYou should use a photo of Salmon Sushi Burrito to trigger the image generation.## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.## Intended uses & limitations#### How to use#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - tonyassi/dolls-kill-club-exx\n\n<Gallery />", "## Model description\n\nThese are tonyassi/dolls-kill-club-exx LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use Dolls Kill Club Exx style to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - tonyassi/dolls-kill-club-exx\n\n<Gallery />", "## Model description\n\nThese are tonyassi/dolls-kill-club-exx LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use Dolls Kill Club Exx style to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ 73, 26, 86, 19, 25, 6, 7, 23, 17 ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - tonyassi/dolls-kill-club-exx\n\n<Gallery />## Model description\n\nThese are tonyassi/dolls-kill-club-exx LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.## Trigger words\n\nYou should use Dolls Kill Club Exx style to trigger the image generation.## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.## Intended uses & limitations#### How to use#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "transformers", "safetensors", "plbart", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #plbart #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 34, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #plbart #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "region:us" ]

[]

[]

[ "# DDPO trained model\n num_epochs=20 \n\n train_gradient_accumulation_steps=1 \n\n sample_num_steps=30 \n\n sample_batch_size=8 \n \n train_batch_size=8 \n\n sample_num_batches_per_epoch=32 \n\n based off of stabilityai/stable-diffusion-2-base\n and then trained off of None" ]

[ "TAGS\n#region-us \n", "# DDPO trained model\n num_epochs=20 \n\n train_gradient_accumulation_steps=1 \n\n sample_num_steps=30 \n\n sample_batch_size=8 \n \n train_batch_size=8 \n\n sample_num_batches_per_epoch=32 \n\n based off of stabilityai/stable-diffusion-2-base\n and then trained off of None" ]

[ 5, 75 ]

[ "TAGS\n#region-us \n# DDPO trained model\n num_epochs=20 \n\n train_gradient_accumulation_steps=1 \n\n sample_num_steps=30 \n\n sample_batch_size=8 \n \n train_batch_size=8 \n\n sample_num_batches_per_epoch=32 \n\n based off of stabilityai/stable-diffusion-2-base\n and then trained off of None" ]

[ "facebook", "meta", "pytorch", "llama", "llama-3", "axolotl", "text-generation", "en", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#facebook #meta #pytorch #llama #llama-3 #axolotl #text-generation #en #region-us \n" ]

[ 32 ]

[ "TAGS\n#facebook #meta #pytorch #llama #llama-3 #axolotl #text-generation #en #region-us \n" ]

[ "gguf", "GGUF", "iMat", "llama3", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "## Poppy_Porpoise-DADA-8B-iMat-GGUF\n\n\nQuantized from fp16 with love.\n* Weighted quantizations were calculated with fp16 GGUF using groups_merged.txt in 105 chunks (recommended amount for this file) and n_ctx=512. Special thanks to jukofyork for sharing this process\n\n<b>Important Note - Quantized post PR6920. There may still be some remaining issues with the bpe tokenizer so consider these quantizations experimental for now. Any feedback is greatly encouraged. In initial tests quants as low as Q2_K can still answer math questions.</b>\n\n\nFor a brief rundown of iMatrix quant performance please see this PR\n\n<b>All quants are verified working prior to uploading to repo for your safety and convenience. </b>\n\nIt's highly recommended to stick to higher quants of this model due to the unique nature of its pseudotokens\n\nOriginal model card here and below\n\n---", "# This is a DADA tuned version of ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B", "### As always, experimental model, results may be unpredictable. \n\n![](URL\n\nThe intermediate merge model was finetuned specifically for the original model and then merged onto it via 50/50 SLERP merge.\n\nAs far as RP goes my current testing setup is having difficulties involving end of sequence and I found the prompt templates provided with Poppy Porpoise were not yielding desirable results on either the original model or the DADA tune so I opted instead to use Libra style Llama-3 prompt templates and simple sampling. The results, albeit subjective, I thought were good.", "## Whether or not the tune had any effect on multi-modal capabilities was not part of the test and instead focus was entirely on creative writing.\n\nTest: A simple instruct prompt utilizing determinsitic samplers.\n\nPROMPT\n\n\nPoppy Porpoise Original:\n\n\n\nPoppy Porpoise DADA\n\n\n\nAs you can clearly see the cadence and overall word selection by the DADA model is more copacetic with what would be expected from a gothic metal duet indicating that the IQ of the model has increased by at least 100 points. \n\nTraining was done using qlora-pipe" ]

[ "TAGS\n#gguf #GGUF #iMat #llama3 #license-cc-by-nc-4.0 #region-us \n", "## Poppy_Porpoise-DADA-8B-iMat-GGUF\n\n\nQuantized from fp16 with love.\n* Weighted quantizations were calculated with fp16 GGUF using groups_merged.txt in 105 chunks (recommended amount for this file) and n_ctx=512. Special thanks to jukofyork for sharing this process\n\n<b>Important Note - Quantized post PR6920. There may still be some remaining issues with the bpe tokenizer so consider these quantizations experimental for now. Any feedback is greatly encouraged. In initial tests quants as low as Q2_K can still answer math questions.</b>\n\n\nFor a brief rundown of iMatrix quant performance please see this PR\n\n<b>All quants are verified working prior to uploading to repo for your safety and convenience. </b>\n\nIt's highly recommended to stick to higher quants of this model due to the unique nature of its pseudotokens\n\nOriginal model card here and below\n\n---", "# This is a DADA tuned version of ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B", "### As always, experimental model, results may be unpredictable. \n\n![](URL\n\nThe intermediate merge model was finetuned specifically for the original model and then merged onto it via 50/50 SLERP merge.\n\nAs far as RP goes my current testing setup is having difficulties involving end of sequence and I found the prompt templates provided with Poppy Porpoise were not yielding desirable results on either the original model or the DADA tune so I opted instead to use Libra style Llama-3 prompt templates and simple sampling. The results, albeit subjective, I thought were good.", "## Whether or not the tune had any effect on multi-modal capabilities was not part of the test and instead focus was entirely on creative writing.\n\nTest: A simple instruct prompt utilizing determinsitic samplers.\n\nPROMPT\n\n\nPoppy Porpoise Original:\n\n\n\nPoppy Porpoise DADA\n\n\n\nAs you can clearly see the cadence and overall word selection by the DADA model is more copacetic with what would be expected from a gothic metal duet indicating that the IQ of the model has increased by at least 100 points. \n\nTraining was done using qlora-pipe" ]

[ 32, 222, 31, 123, 113 ]

[ "TAGS\n#gguf #GGUF #iMat #llama3 #license-cc-by-nc-4.0 #region-us \n## Poppy_Porpoise-DADA-8B-iMat-GGUF\n\n\nQuantized from fp16 with love.\n* Weighted quantizations were calculated with fp16 GGUF using groups_merged.txt in 105 chunks (recommended amount for this file) and n_ctx=512. Special thanks to jukofyork for sharing this process\n\n<b>Important Note - Quantized post PR6920. There may still be some remaining issues with the bpe tokenizer so consider these quantizations experimental for now. Any feedback is greatly encouraged. In initial tests quants as low as Q2_K can still answer math questions.</b>\n\n\nFor a brief rundown of iMatrix quant performance please see this PR\n\n<b>All quants are verified working prior to uploading to repo for your safety and convenience. </b>\n\nIt's highly recommended to stick to higher quants of this model due to the unique nature of its pseudotokens\n\nOriginal model card here and below\n\n---# This is a DADA tuned version of ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B### As always, experimental model, results may be unpredictable. \n\n![](URL\n\nThe intermediate merge model was finetuned specifically for the original model and then merged onto it via 50/50 SLERP merge.\n\nAs far as RP goes my current testing setup is having difficulties involving end of sequence and I found the prompt templates provided with Poppy Porpoise were not yielding desirable results on either the original model or the DADA tune so I opted instead to use Libra style Llama-3 prompt templates and simple sampling. The results, albeit subjective, I thought were good.## Whether or not the tune had any effect on multi-modal capabilities was not part of the test and instead focus was entirely on creative writing.\n\nTest: A simple instruct prompt utilizing determinsitic samplers.\n\nPROMPT\n\n\nPoppy Porpoise Original:\n\n\n\nPoppy Porpoise DADA\n\n\n\nAs you can clearly see the cadence and overall word selection by the DADA model is more copacetic with what would be expected from a gothic metal duet indicating that the IQ of the model has increased by at least 100 points. \n\nTraining was done using qlora-pipe" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 32, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tr", "license:mit", "endpoints_compatible", "region:us" ]

[]

[ "tr" ]

[ "# TS-Corpus WordPiece Tokenizer (256k, Cased)", "## Overview\nThis repository contains a WordPiece tokenizer with a vocabulary size of 256,000, trained uncased on various datasets from the TS Corpus website. It is designed to handle Turkish text, leveraging rich and diverse sources to provide a robust tool for natural language processing tasks.", "## Dataset Sources\nThe tokenizer was trained using multiple corpora from the TS Corpus, specifically:\n- TS Corpus V2\n- TS Wikipedia Corpus\n- TS Abstract Corpus\n- TS Idioms and Proverbs Corpus\n- Syllable Corpus\n- Turkish Constitution Corpus\n\nThese diverse sources include a wide range of texts from encyclopedic articles to legal documents, providing a comprehensive linguistic foundation for the tokenizer.", "## Tokenizer Model\nThe tokenizer uses the WordPiece model, which is widely utilized in many modern NLP systems. It is particularly effective in handling languages with rich morphology like Turkish due to its subword segmentation approach. This tokenizer differentiates between uppercase and lowercase letters.", "## Usage\nTo use this tokenizer, you can load it via the Hugging Face 'transformers' library as follows:" ]

[ "TAGS\n#transformers #tr #license-mit #endpoints_compatible #region-us \n", "# TS-Corpus WordPiece Tokenizer (256k, Cased)", "## Overview\nThis repository contains a WordPiece tokenizer with a vocabulary size of 256,000, trained uncased on various datasets from the TS Corpus website. It is designed to handle Turkish text, leveraging rich and diverse sources to provide a robust tool for natural language processing tasks.", "## Dataset Sources\nThe tokenizer was trained using multiple corpora from the TS Corpus, specifically:\n- TS Corpus V2\n- TS Wikipedia Corpus\n- TS Abstract Corpus\n- TS Idioms and Proverbs Corpus\n- Syllable Corpus\n- Turkish Constitution Corpus\n\nThese diverse sources include a wide range of texts from encyclopedic articles to legal documents, providing a comprehensive linguistic foundation for the tokenizer.", "## Tokenizer Model\nThe tokenizer uses the WordPiece model, which is widely utilized in many modern NLP systems. It is particularly effective in handling languages with rich morphology like Turkish due to its subword segmentation approach. This tokenizer differentiates between uppercase and lowercase letters.", "## Usage\nTo use this tokenizer, you can load it via the Hugging Face 'transformers' library as follows:" ]

[ 18, 15, 59, 80, 59, 24 ]

[ "TAGS\n#transformers #tr #license-mit #endpoints_compatible #region-us \n# TS-Corpus WordPiece Tokenizer (256k, Cased)## Overview\nThis repository contains a WordPiece tokenizer with a vocabulary size of 256,000, trained uncased on various datasets from the TS Corpus website. It is designed to handle Turkish text, leveraging rich and diverse sources to provide a robust tool for natural language processing tasks.## Dataset Sources\nThe tokenizer was trained using multiple corpora from the TS Corpus, specifically:\n- TS Corpus V2\n- TS Wikipedia Corpus\n- TS Abstract Corpus\n- TS Idioms and Proverbs Corpus\n- Syllable Corpus\n- Turkish Constitution Corpus\n\nThese diverse sources include a wide range of texts from encyclopedic articles to legal documents, providing a comprehensive linguistic foundation for the tokenizer.## Tokenizer Model\nThe tokenizer uses the WordPiece model, which is widely utilized in many modern NLP systems. It is particularly effective in handling languages with rich morphology like Turkish due to its subword segmentation approach. This tokenizer differentiates between uppercase and lowercase letters.## Usage\nTo use this tokenizer, you can load it via the Hugging Face 'transformers' library as follows:" ]

[ "license:mit", "region:us" ]

[]

[]

[ "# TS-Corpus BPE Tokenizer (256k, Cased)", "## Overview\nThis repository hosts a Byte Pair Encoding (BPE) tokenizer with a vocabulary size of 256,000, trained cased using several datasets from the TS Corpus website. The BPE method is particularly effective for languages like Turkish, providing a balance between word-level and character-level tokenization.", "## Dataset Sources\nThe tokenizer was trained on a variety of text sources from TS Corpus, ensuring a broad linguistic coverage. These sources include:\n- TS Corpus V2\n- TS Wikipedia Corpus\n- TS Abstract Corpus\n- TS Idioms and Proverbs Corpus\n- Syllable Corpus\n- Turkish Constitution Corpus\n\nThe inclusion of idiomatic expressions, proverbs, and legal terminology provides a comprehensive toolkit for processing Turkish text across different domains.", "## Tokenizer Model\nUtilizing the Byte Pair Encoding (BPE) method, this tokenizer excels in efficiently managing subword units without the need for an extensive vocabulary. BPE is especially suitable for handling the agglutinative nature of Turkish, where words can have multiple suffixes.", "## Usage\nTo use this tokenizer in your projects, load it with the Hugging Face 'transformers' library:" ]

[ "TAGS\n#license-mit #region-us \n", "# TS-Corpus BPE Tokenizer (256k, Cased)", "## Overview\nThis repository hosts a Byte Pair Encoding (BPE) tokenizer with a vocabulary size of 256,000, trained cased using several datasets from the TS Corpus website. The BPE method is particularly effective for languages like Turkish, providing a balance between word-level and character-level tokenization.", "## Dataset Sources\nThe tokenizer was trained on a variety of text sources from TS Corpus, ensuring a broad linguistic coverage. These sources include:\n- TS Corpus V2\n- TS Wikipedia Corpus\n- TS Abstract Corpus\n- TS Idioms and Proverbs Corpus\n- Syllable Corpus\n- Turkish Constitution Corpus\n\nThe inclusion of idiomatic expressions, proverbs, and legal terminology provides a comprehensive toolkit for processing Turkish text across different domains.", "## Tokenizer Model\nUtilizing the Byte Pair Encoding (BPE) method, this tokenizer excels in efficiently managing subword units without the need for an extensive vocabulary. BPE is especially suitable for handling the agglutinative nature of Turkish, where words can have multiple suffixes.", "## Usage\nTo use this tokenizer in your projects, load it with the Hugging Face 'transformers' library:" ]

[ 9, 15, 65, 87, 60, 23 ]

[ "TAGS\n#license-mit #region-us \n# TS-Corpus BPE Tokenizer (256k, Cased)## Overview\nThis repository hosts a Byte Pair Encoding (BPE) tokenizer with a vocabulary size of 256,000, trained cased using several datasets from the TS Corpus website. The BPE method is particularly effective for languages like Turkish, providing a balance between word-level and character-level tokenization.## Dataset Sources\nThe tokenizer was trained on a variety of text sources from TS Corpus, ensuring a broad linguistic coverage. These sources include:\n- TS Corpus V2\n- TS Wikipedia Corpus\n- TS Abstract Corpus\n- TS Idioms and Proverbs Corpus\n- Syllable Corpus\n- Turkish Constitution Corpus\n\nThe inclusion of idiomatic expressions, proverbs, and legal terminology provides a comprehensive toolkit for processing Turkish text across different domains.## Tokenizer Model\nUtilizing the Byte Pair Encoding (BPE) method, this tokenizer excels in efficiently managing subword units without the need for an extensive vocabulary. BPE is especially suitable for handling the agglutinative nature of Turkish, where words can have multiple suffixes.## Usage\nTo use this tokenizer in your projects, load it with the Hugging Face 'transformers' library:" ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

[]

[]

[ "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"arienmixxl-asian-portrait\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"arienmixxl-asian-portrait\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"arienmixxl-asian-portrait\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"arienmixxl-asian-portrait\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ 56, 8, 519 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n# API Inference\n\n!generated from URL## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"arienmixxl-asian-portrait\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"arienmixxl-asian-portrait\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "transformers", "safetensors", "gpt_neo", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neo #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 40, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neo #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "mlx", "safetensors", "llama", "generated_from_trainer", "axolotl", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "region:us" ]

[]

[]

[ "# mlx-community/dolphin-2.9-llama3-8b-1m-4bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-8b-1m']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #generated_from_trainer #axolotl #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n", "# mlx-community/dolphin-2.9-llama3-8b-1m-4bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-8b-1m']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ 193, 85, 6 ]

[ "TAGS\n#mlx #safetensors #llama #generated_from_trainer #axolotl #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n# mlx-community/dolphin-2.9-llama3-8b-1m-4bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-8b-1m']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.## Use with mlx" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 22, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "shanchen/llama3-8B-slerp-med-chinese", "shenzhi-wang/Llama3-8B-Chinese-Chat", "conversational", "zh", "en", "base_model:shanchen/llama3-8B-slerp-med-chinese", "base_model:shenzhi-wang/Llama3-8B-Chinese-Chat", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "zh", "en" ]

[ "# llama3-8B-slerp-biomed-chat-chinese\n\nllama3-8B-slerp-biomed-chat-chinese is a merge of the following models using LazyMergekit:\n* shanchen/llama3-8B-slerp-med-chinese\n* shenzhi-wang/Llama3-8B-Chinese-Chat", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #shanchen/llama3-8B-slerp-med-chinese #shenzhi-wang/Llama3-8B-Chinese-Chat #conversational #zh #en #base_model-shanchen/llama3-8B-slerp-med-chinese #base_model-shenzhi-wang/Llama3-8B-Chinese-Chat #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# llama3-8B-slerp-biomed-chat-chinese\n\nllama3-8B-slerp-biomed-chat-chinese is a merge of the following models using LazyMergekit:\n* shanchen/llama3-8B-slerp-med-chinese\n* shenzhi-wang/Llama3-8B-Chinese-Chat", "## Configuration", "## Usage" ]

[ 134, 82, 3, 3 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #shanchen/llama3-8B-slerp-med-chinese #shenzhi-wang/Llama3-8B-Chinese-Chat #conversational #zh #en #base_model-shanchen/llama3-8B-slerp-med-chinese #base_model-shenzhi-wang/Llama3-8B-Chinese-Chat #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# llama3-8B-slerp-biomed-chat-chinese\n\nllama3-8B-slerp-biomed-chat-chinese is a merge of the following models using LazyMergekit:\n* shanchen/llama3-8B-slerp-med-chinese\n* shenzhi-wang/Llama3-8B-Chinese-Chat## Configuration## Usage" ]

[ "gguf", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #region-us \n" ]

[ 9 ]

[ "TAGS\n#gguf #region-us \n" ]

[ "safetensors", "arxiv:2310.03744", "arxiv:2304.08485", "arxiv:2311.05437", "arxiv:2311.00571", "arxiv:2306.00890", "arxiv:2309.09958", "arxiv:2309.10020", "arxiv:2306.14895", "arxiv:2112.05682", "endpoints_compatible", "region:us" ]

[ "2310.03744", "2304.08485", "2311.05437", "2311.00571", "2306.00890", "2309.09958", "2309.10020", "2306.14895", "2112.05682" ]

[]

[ "### Hyperparameters\n\n\nWe use a similar set of hyperparameters as Vicuna in finetuning. Both hyperparameters used in pretraining and finetuning are provided below.\n\n\n1. Pretraining\n\n\n\n2. Finetuning", "### Download Vicuna checkpoints (automatically)\n\n\nOur base model Vicuna v1.5, which is an instruction-tuned chatbot, will be downloaded automatically when you run our provided training scripts. No action is needed.", "### Pretrain (feature alignment)\n\n\nPlease download the 558K subset of the LAION-CC-SBU dataset with BLIP captions we use in the paper here.\n\n\nPretrain takes around 5.5 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 3.5 hours for LLaVA-v1.5-7B.\n\n\nTraining script with DeepSpeed ZeRO-2: 'URL'.\n\n\n* '--mm\\_projector\\_type mlp2x\\_gelu': the two-layer MLP vision-language connector.\n* '--vision\\_tower openai/clip-vit-large-patch14-336': CLIP ViT-L/14 336px.\n\n\n\nPretrain takes around 20 hours for LLaVA-7B on 8x V100 (32G)\nWe provide training script with DeepSpeed here.\nTips:\n\n\n* If you are using V100 which is not supported by FlashAttention, you can use the memory-efficient attention implemented in xFormers. Install xformers and replace 'llava/train/train\\_mem.py' above with llava/train/train\\_xformers.py.", "### Visual Instruction Tuning\n\n\n1. Prepare data\n\n\nPlease download the annotation of the final mixture our instruction tuning data llava\\_v1\\_5\\_mix665k.json, and download the images from constituting datasets:\n\n\n* COCO: train2017\n* GQA: images\n* OCR-VQA: download script, we save all files as '.jpg'\n* TextVQA: train\\_val\\_images\n* VisualGenome: part1, part2\n\n\nAfter downloading all of them, organize the data as follows in './playground/data',\n\n\n2. Start training!\n\n\nYou may download our pretrained projectors in Model Zoo. It is not recommended to use legacy projectors, as they may be trained with a different version of the codebase, and if any option is off, the model will not function/train as we expected.\n\n\nVisual instruction tuning takes around 20 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 10 hours for LLaVA-v1.5-7B on 8x A100 (40G).\n\n\nTraining script with DeepSpeed ZeRO-3: 'URL'.\n\n\nIf you are do not have enough GPU memory:\n\n\n* Use LoRA: 'finetune\\_lora.sh'. We are able to fit 13B training in 8-A100-40G/8-A6000, and 7B training in 8-RTX3090. Make sure 'per\\_device\\_train\\_batch\\_size\\*gradient\\_accumulation\\_steps' is the same as the provided script for best reproducibility.\n* Replace 'URL' with 'zero3\\_offload.json' which offloads some parameters to CPU RAM. This slows down the training speed.\n\n\nIf you are interested in finetuning LLaVA model to your own task/data, please check out 'Finetune\\_Custom\\_Data.md'。\n\n\nNew options to note:\n\n\n* '--mm\\_projector\\_type mlp2x\\_gelu': the two-layer MLP vision-language connector.\n* '--vision\\_tower openai/clip-vit-large-patch14-336': CLIP ViT-L/14 336px.\n* '--image\\_aspect\\_ratio pad': this pads the non-square images to square, instead of cropping them; it slightly reduces hallucination.\n* '--group\\_by\\_modality\\_length True': this should only be used when your instruction tuning dataset contains both language (e.g. ShareGPT) and multimodal (e.g. LLaVA-Instruct). It makes the training sampler only sample a single modality (either image or language) during training, which we observe to speed up training by ~25%, and does not affect the final outcome.\n\n\nEvaluation\n----------\n\n\nIn LLaVA-1.5, we evaluate models on a diverse set of 12 benchmarks. To ensure the reproducibility, we evaluate the models with greedy decoding. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs.\n\n\nSee URL.", "### GPT-assisted Evaluation\n\n\nOur GPT-assisted evaluation pipeline for multimodal modeling is provided for a comprehensive understanding of the capabilities of vision-language models. Please see our paper for more details.\n\n\n1. Generate LLaVA responses\n2. Evaluate the generated responses. In our case, 'URL' is the response generated by text-only GPT-4 (0314), with the context captions/boxes provided.\n3. Summarize the evaluation results\n\n\nIf you find LLaVA useful for your research and applications, please cite using this BibTeX:\n\n\nAcknowledgement\n---------------\n\n\n* Vicuna: the codebase we built upon, and our base model Vicuna-13B that has the amazing language capabilities!\n\n\nRelated Projects\n----------------\n\n\n* Instruction Tuning with GPT-4\n* LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day\n* Otter: In-Context Multi-Modal Instruction Tuning\n\n\nFor future project ideas, please check out:\n\n\n* SEEM: Segment Everything Everywhere All at Once\n* Grounded-Segment-Anything to detect, segment, and generate anything by marrying Grounding DINO and Segment-Anything." ]

[ "TAGS\n#safetensors #arxiv-2310.03744 #arxiv-2304.08485 #arxiv-2311.05437 #arxiv-2311.00571 #arxiv-2306.00890 #arxiv-2309.09958 #arxiv-2309.10020 #arxiv-2306.14895 #arxiv-2112.05682 #endpoints_compatible #region-us \n", "### Hyperparameters\n\n\nWe use a similar set of hyperparameters as Vicuna in finetuning. Both hyperparameters used in pretraining and finetuning are provided below.\n\n\n1. Pretraining\n\n\n\n2. Finetuning", "### Download Vicuna checkpoints (automatically)\n\n\nOur base model Vicuna v1.5, which is an instruction-tuned chatbot, will be downloaded automatically when you run our provided training scripts. No action is needed.", "### Pretrain (feature alignment)\n\n\nPlease download the 558K subset of the LAION-CC-SBU dataset with BLIP captions we use in the paper here.\n\n\nPretrain takes around 5.5 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 3.5 hours for LLaVA-v1.5-7B.\n\n\nTraining script with DeepSpeed ZeRO-2: 'URL'.\n\n\n* '--mm\\_projector\\_type mlp2x\\_gelu': the two-layer MLP vision-language connector.\n* '--vision\\_tower openai/clip-vit-large-patch14-336': CLIP ViT-L/14 336px.\n\n\n\nPretrain takes around 20 hours for LLaVA-7B on 8x V100 (32G)\nWe provide training script with DeepSpeed here.\nTips:\n\n\n* If you are using V100 which is not supported by FlashAttention, you can use the memory-efficient attention implemented in xFormers. Install xformers and replace 'llava/train/train\\_mem.py' above with llava/train/train\\_xformers.py.", "### Visual Instruction Tuning\n\n\n1. Prepare data\n\n\nPlease download the annotation of the final mixture our instruction tuning data llava\\_v1\\_5\\_mix665k.json, and download the images from constituting datasets:\n\n\n* COCO: train2017\n* GQA: images\n* OCR-VQA: download script, we save all files as '.jpg'\n* TextVQA: train\\_val\\_images\n* VisualGenome: part1, part2\n\n\nAfter downloading all of them, organize the data as follows in './playground/data',\n\n\n2. Start training!\n\n\nYou may download our pretrained projectors in Model Zoo. It is not recommended to use legacy projectors, as they may be trained with a different version of the codebase, and if any option is off, the model will not function/train as we expected.\n\n\nVisual instruction tuning takes around 20 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 10 hours for LLaVA-v1.5-7B on 8x A100 (40G).\n\n\nTraining script with DeepSpeed ZeRO-3: 'URL'.\n\n\nIf you are do not have enough GPU memory:\n\n\n* Use LoRA: 'finetune\\_lora.sh'. We are able to fit 13B training in 8-A100-40G/8-A6000, and 7B training in 8-RTX3090. Make sure 'per\\_device\\_train\\_batch\\_size\\*gradient\\_accumulation\\_steps' is the same as the provided script for best reproducibility.\n* Replace 'URL' with 'zero3\\_offload.json' which offloads some parameters to CPU RAM. This slows down the training speed.\n\n\nIf you are interested in finetuning LLaVA model to your own task/data, please check out 'Finetune\\_Custom\\_Data.md'。\n\n\nNew options to note:\n\n\n* '--mm\\_projector\\_type mlp2x\\_gelu': the two-layer MLP vision-language connector.\n* '--vision\\_tower openai/clip-vit-large-patch14-336': CLIP ViT-L/14 336px.\n* '--image\\_aspect\\_ratio pad': this pads the non-square images to square, instead of cropping them; it slightly reduces hallucination.\n* '--group\\_by\\_modality\\_length True': this should only be used when your instruction tuning dataset contains both language (e.g. ShareGPT) and multimodal (e.g. LLaVA-Instruct). It makes the training sampler only sample a single modality (either image or language) during training, which we observe to speed up training by ~25%, and does not affect the final outcome.\n\n\nEvaluation\n----------\n\n\nIn LLaVA-1.5, we evaluate models on a diverse set of 12 benchmarks. To ensure the reproducibility, we evaluate the models with greedy decoding. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs.\n\n\nSee URL.", "### GPT-assisted Evaluation\n\n\nOur GPT-assisted evaluation pipeline for multimodal modeling is provided for a comprehensive understanding of the capabilities of vision-language models. Please see our paper for more details.\n\n\n1. Generate LLaVA responses\n2. Evaluate the generated responses. In our case, 'URL' is the response generated by text-only GPT-4 (0314), with the context captions/boxes provided.\n3. Summarize the evaluation results\n\n\nIf you find LLaVA useful for your research and applications, please cite using this BibTeX:\n\n\nAcknowledgement\n---------------\n\n\n* Vicuna: the codebase we built upon, and our base model Vicuna-13B that has the amazing language capabilities!\n\n\nRelated Projects\n----------------\n\n\n* Instruction Tuning with GPT-4\n* LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day\n* Otter: In-Context Multi-Modal Instruction Tuning\n\n\nFor future project ideas, please check out:\n\n\n* SEEM: Segment Everything Everywhere All at Once\n* Grounded-Segment-Anything to detect, segment, and generate anything by marrying Grounding DINO and Segment-Anything." ]

[ 113, 53, 47, 282, 724, 265 ]

[ "TAGS\n#safetensors #arxiv-2310.03744 #arxiv-2304.08485 #arxiv-2311.05437 #arxiv-2311.00571 #arxiv-2306.00890 #arxiv-2309.09958 #arxiv-2309.10020 #arxiv-2306.14895 #arxiv-2112.05682 #endpoints_compatible #region-us \n### Hyperparameters\n\n\nWe use a similar set of hyperparameters as Vicuna in finetuning. Both hyperparameters used in pretraining and finetuning are provided below.\n\n\n1. Pretraining\n\n\n\n2. Finetuning### Download Vicuna checkpoints (automatically)\n\n\nOur base model Vicuna v1.5, which is an instruction-tuned chatbot, will be downloaded automatically when you run our provided training scripts. No action is needed.### Pretrain (feature alignment)\n\n\nPlease download the 558K subset of the LAION-CC-SBU dataset with BLIP captions we use in the paper here.\n\n\nPretrain takes around 5.5 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 3.5 hours for LLaVA-v1.5-7B.\n\n\nTraining script with DeepSpeed ZeRO-2: 'URL'.\n\n\n* '--mm\\_projector\\_type mlp2x\\_gelu': the two-layer MLP vision-language connector.\n* '--vision\\_tower openai/clip-vit-large-patch14-336': CLIP ViT-L/14 336px.\n\n\n\nPretrain takes around 20 hours for LLaVA-7B on 8x V100 (32G)\nWe provide training script with DeepSpeed here.\nTips:\n\n\n* If you are using V100 which is not supported by FlashAttention, you can use the memory-efficient attention implemented in xFormers. Install xformers and replace 'llava/train/train\\_mem.py' above with llava/train/train\\_xformers.py.### Visual Instruction Tuning\n\n\n1. Prepare data\n\n\nPlease download the annotation of the final mixture our instruction tuning data llava\\_v1\\_5\\_mix665k.json, and download the images from constituting datasets:\n\n\n* COCO: train2017\n* GQA: images\n* OCR-VQA: download script, we save all files as '.jpg'\n* TextVQA: train\\_val\\_images\n* VisualGenome: part1, part2\n\n\nAfter downloading all of them, organize the data as follows in './playground/data',\n\n\n2. Start training!\n\n\nYou may download our pretrained projectors in Model Zoo. It is not recommended to use legacy projectors, as they may be trained with a different version of the codebase, and if any option is off, the model will not function/train as we expected.\n\n\nVisual instruction tuning takes around 20 hours for LLaVA-v1.5-13B on 8x A100 (80G), due to the increased resolution to 336px. It takes around 10 hours for LLaVA-v1.5-7B on 8x A100 (40G).\n\n\nTraining script with DeepSpeed ZeRO-3: 'URL'.\n\n\nIf you are do not have enough GPU memory:\n\n\n* Use LoRA: 'finetune\\_lora.sh'. We are able to fit 13B training in 8-A100-40G/8-A6000, and 7B training in 8-RTX3090. Make sure 'per\\_device\\_train\\_batch\\_size\\*gradient\\_accumulation\\_steps' is the same as the provided script for best reproducibility.\n* Replace 'URL' with 'zero3\\_offload.json' which offloads some parameters to CPU RAM. This slows down the training speed.\n\n\nIf you are interested in finetuning LLaVA model to your own task/data, please check out 'Finetune\\_Custom\\_Data.md'。\n\n\nNew options to note:\n\n\n* '--mm\\_projector\\_type mlp2x\\_gelu': the two-layer MLP vision-language connector.\n* '--vision\\_tower openai/clip-vit-large-patch14-336': CLIP ViT-L/14 336px.\n* '--image\\_aspect\\_ratio pad': this pads the non-square images to square, instead of cropping them; it slightly reduces hallucination.\n* '--group\\_by\\_modality\\_length True': this should only be used when your instruction tuning dataset contains both language (e.g. ShareGPT) and multimodal (e.g. LLaVA-Instruct). It makes the training sampler only sample a single modality (either image or language) during training, which we observe to speed up training by ~25%, and does not affect the final outcome.\n\n\nEvaluation\n----------\n\n\nIn LLaVA-1.5, we evaluate models on a diverse set of 12 benchmarks. To ensure the reproducibility, we evaluate the models with greedy decoding. We do not evaluate using beam search to make the inference process consistent with the chat demo of real-time outputs.\n\n\nSee URL.### GPT-assisted Evaluation\n\n\nOur GPT-assisted evaluation pipeline for multimodal modeling is provided for a comprehensive understanding of the capabilities of vision-language models. Please see our paper for more details.\n\n\n1. Generate LLaVA responses\n2. Evaluate the generated responses. In our case, 'URL' is the response generated by text-only GPT-4 (0314), with the context captions/boxes provided.\n3. Summarize the evaluation results\n\n\nIf you find LLaVA useful for your research and applications, please cite using this BibTeX:\n\n\nAcknowledgement\n---------------\n\n\n* Vicuna: the codebase we built upon, and our base model Vicuna-13B that has the amazing language capabilities!\n\n\nRelated Projects\n----------------\n\n\n* Instruction Tuning with GPT-4\n* LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day\n* Otter: In-Context Multi-Modal Instruction Tuning\n\n\nFor future project ideas, please check out:\n\n\n* SEEM: Segment Everything Everywhere All at Once\n* Grounded-Segment-Anything to detect, segment, and generate anything by marrying Grounding DINO and Segment-Anything." ]

[ "mlx", "safetensors", "llama", "generated_from_trainer", "axolotl", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "region:us" ]

[]

[]

[ "# mlx-community/dolphin-2.9-llama3-8b-1m-8bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-8b-1m']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #generated_from_trainer #axolotl #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n", "# mlx-community/dolphin-2.9-llama3-8b-1m-8bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-8b-1m']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ 193, 85, 6 ]

[ "TAGS\n#mlx #safetensors #llama #generated_from_trainer #axolotl #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n# mlx-community/dolphin-2.9-llama3-8b-1m-8bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-8b-1m']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.## Use with mlx" ]

[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# CodeQwen1.5-7B-Chat", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance in text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# CodeQwen1.5-7B-Chat", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance in text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ 42, 12, 119, 60, 44, 37, 51 ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# CodeQwen1.5-7B-Chat## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance in text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "transformers", "safetensors", "mt5", "text2text-generation", "generated_from_trainer", "base_model:samzirbo/mT5.pretrained.en-es.16K", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# URL\n\nThis model is a fine-tuned version of samzirbo/URL-es.16K on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4559\n- eval_bleu: 23.0583\n- eval_meteor: 0.5191\n- eval_chrF++: 46.831\n- eval_runtime: 59.5279\n- eval_samples_per_second: 33.598\n- eval_steps_per_second: 0.538\n- epoch: 0.4360\n- step: 4000", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 64\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 3", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mt5 #text2text-generation #generated_from_trainer #base_model-samzirbo/mT5.pretrained.en-es.16K #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# URL\n\nThis model is a fine-tuned version of samzirbo/URL-es.16K on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4559\n- eval_bleu: 23.0583\n- eval_meteor: 0.5191\n- eval_chrF++: 46.831\n- eval_runtime: 59.5279\n- eval_samples_per_second: 33.598\n- eval_steps_per_second: 0.538\n- epoch: 0.4360\n- step: 4000", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 64\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 3", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 65, 139, 7, 9, 9, 4, 108, 44 ]

[ "TAGS\n#transformers #safetensors #mt5 #text2text-generation #generated_from_trainer #base_model-samzirbo/mT5.pretrained.en-es.16K #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# URL\n\nThis model is a fine-tuned version of samzirbo/URL-es.16K on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4559\n- eval_bleu: 23.0583\n- eval_meteor: 0.5191\n- eval_chrF++: 46.831\n- eval_runtime: 59.5279\n- eval_samples_per_second: 33.598\n- eval_steps_per_second: 0.538\n- epoch: 0.4360\n- step: 4000## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 64\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 3### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "license:creativeml-openrail-m", "region:us" ]

[]

[]

[ "## FRANKENWEIGHTS\n\ndunh dunh dunh...\n\nYou wouldn't think something like this might work, but it does. I took the text encoder from my \"Storytime\" model\nand then blindly pasted it over the text encoder stuff in the SD 1.5 model and now we have !FrankenWeights\nIt's ALIVE!!!:\n\n\n\n\n\nAlso included here is a somewhat \"refined\" version of the \"Superposition\" ComfyUI workflow called !Frankenposition This includes\nthe extra awesomesauce done by ByteDance with their work on !Hyper-SD and their \n!Lora for SD1.5 models, which allows you to greatly reduce the steps required to produce an image --\n\n\n\nFrakenweights in this context responds best to \"normal\" CFG ranges (5-8), especially with the Lora linked above. I generally\nlike to make things that will take a huge range of CFG values, but in this case everything hums along together so well\nfor my purposes that I'm not gonna mess with a good thing. We hack stuff and just try things in these parts, and it \njust so happens that the combo of FrankenWeights, that Lora, and the \"Superposition\" bits make a truly Frank-en Stein \nwith enough ummph to bring all your wild ideas to life:\n\n\n\n\n\n\n\n\n\n\n\n\n\n(all of the above come from the same prompts and settings)\n\nSo, get your grubby little hands (I'm sure space aliens consider us to be \"grubby\" and \"little\") on FrankenWeights today.\nI have intentionally left this as a 32 bit model, because more often than not the \"burn\" in an image can be stretched\nlike tasty taffy back into reasonable colors using various image editing things like Photoshop. 32 bits per pixel gives\na _huge_ range of latitude for adjusting colors in such programs. I imagine most colorists would be in heaven if there\nwas some video codec that could work at 32 bits. So, welcome to, uh, \"heaven\" and go to town on even your burnt images\nbecause there's all sorts of latitude with 32 bits." ]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n", "## FRANKENWEIGHTS\n\ndunh dunh dunh...\n\nYou wouldn't think something like this might work, but it does. I took the text encoder from my \"Storytime\" model\nand then blindly pasted it over the text encoder stuff in the SD 1.5 model and now we have !FrankenWeights\nIt's ALIVE!!!:\n\n\n\n\n\nAlso included here is a somewhat \"refined\" version of the \"Superposition\" ComfyUI workflow called !Frankenposition This includes\nthe extra awesomesauce done by ByteDance with their work on !Hyper-SD and their \n!Lora for SD1.5 models, which allows you to greatly reduce the steps required to produce an image --\n\n\n\nFrakenweights in this context responds best to \"normal\" CFG ranges (5-8), especially with the Lora linked above. I generally\nlike to make things that will take a huge range of CFG values, but in this case everything hums along together so well\nfor my purposes that I'm not gonna mess with a good thing. We hack stuff and just try things in these parts, and it \njust so happens that the combo of FrankenWeights, that Lora, and the \"Superposition\" bits make a truly Frank-en Stein \nwith enough ummph to bring all your wild ideas to life:\n\n\n\n\n\n\n\n\n\n\n\n\n\n(all of the above come from the same prompts and settings)\n\nSo, get your grubby little hands (I'm sure space aliens consider us to be \"grubby\" and \"little\") on FrankenWeights today.\nI have intentionally left this as a 32 bit model, because more often than not the \"burn\" in an image can be stretched\nlike tasty taffy back into reasonable colors using various image editing things like Photoshop. 32 bits per pixel gives\na _huge_ range of latitude for adjusting colors in such programs. I imagine most colorists would be in heaven if there\nwas some video codec that could work at 32 bits. So, welcome to, uh, \"heaven\" and go to town on even your burnt images\nbecause there's all sorts of latitude with 32 bits." ]

[ 15, 571 ]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n## FRANKENWEIGHTS\n\ndunh dunh dunh...\n\nYou wouldn't think something like this might work, but it does. I took the text encoder from my \"Storytime\" model\nand then blindly pasted it over the text encoder stuff in the SD 1.5 model and now we have !FrankenWeights\nIt's ALIVE!!!:\n\n\n\n\n\nAlso included here is a somewhat \"refined\" version of the \"Superposition\" ComfyUI workflow called !Frankenposition This includes\nthe extra awesomesauce done by ByteDance with their work on !Hyper-SD and their \n!Lora for SD1.5 models, which allows you to greatly reduce the steps required to produce an image --\n\n\n\nFrakenweights in this context responds best to \"normal\" CFG ranges (5-8), especially with the Lora linked above. I generally\nlike to make things that will take a huge range of CFG values, but in this case everything hums along together so well\nfor my purposes that I'm not gonna mess with a good thing. We hack stuff and just try things in these parts, and it \njust so happens that the combo of FrankenWeights, that Lora, and the \"Superposition\" bits make a truly Frank-en Stein \nwith enough ummph to bring all your wild ideas to life:\n\n\n\n\n\n\n\n\n\n\n\n\n\n(all of the above come from the same prompts and settings)\n\nSo, get your grubby little hands (I'm sure space aliens consider us to be \"grubby\" and \"little\") on FrankenWeights today.\nI have intentionally left this as a 32 bit model, because more often than not the \"burn\" in an image can be stretched\nlike tasty taffy back into reasonable colors using various image editing things like Photoshop. 32 bits per pixel gives\na _huge_ range of latitude for adjusting colors in such programs. I imagine most colorists would be in heaven if there\nwas some video codec that could work at 32 bits. So, welcome to, uh, \"heaven\" and go to town on even your burnt images\nbecause there's all sorts of latitude with 32 bits." ]

[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - embracellm/sushi10_LoRA\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi10_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Tuna Sushi Burrito to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #dora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - embracellm/sushi10_LoRA\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi10_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Tuna Sushi Burrito to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ 72, 24, 84, 21, 25, 6, 7, 23, 17 ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #dora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - embracellm/sushi10_LoRA\n\n<Gallery />## Model description\n\nThese are embracellm/sushi10_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.## Trigger words\n\nYou should use a photo of Tuna Sushi Burrito to trigger the image generation.## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.## Intended uses & limitations#### How to use#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]

[]

[]

[ "# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: dhajnes/ppo-Pyramids\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us \n", "# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: dhajnes/ppo-Pyramids\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ 35, 199 ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us \n# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: dhajnes/ppo-Pyramids\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "beit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/beit-base-patch16-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 100\n* eval\\_batch\\_size: 100\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 400\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 100", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #beit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/beit-base-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 100\n* eval\\_batch\\_size: 100\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 400\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 100", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 70, 142, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #beit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/beit-base-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 100\n* eval\\_batch\\_size: 100\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 400\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 100### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[]

[ "# CodeQwen1.5-7B-Chat", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance in text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# CodeQwen1.5-7B-Chat", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance in text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ 42, 12, 119, 60, 44, 37, 51 ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n# CodeQwen1.5-7B-Chat## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance in text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "transformers", "gguf", "meta", "llama-3", "en", "base_model:abacusai/Llama-3-Giraffe-70B", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #meta #llama-3 #en #base_model-abacusai/Llama-3-Giraffe-70B #license-llama3 #endpoints_compatible #region-us \n" ]

[ 51 ]

[ "TAGS\n#transformers #gguf #meta #llama-3 #en #base_model-abacusai/Llama-3-Giraffe-70B #license-llama3 #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "led", "text2text-generation", "summarization", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# BioNLP-tech-decoder-eLife\n\nThis model was trained from scratch on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.3739167643078955e-06\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 1.13.1+cu117\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #led #text2text-generation #summarization #generated_from_trainer #autotrain_compatible #endpoints_compatible #region-us \n", "# BioNLP-tech-decoder-eLife\n\nThis model was trained from scratch on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.3739167643078955e-06\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 1.13.1+cu117\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ 39, 24, 7, 9, 9, 4, 122, 5, 44 ]

[ "TAGS\n#transformers #safetensors #led #text2text-generation #summarization #generated_from_trainer #autotrain_compatible #endpoints_compatible #region-us \n# BioNLP-tech-decoder-eLife\n\nThis model was trained from scratch on an unknown dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.3739167643078955e-06\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5\n- mixed_precision_training: Native AMP### Training results### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 1.13.1+cu117\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

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

[]

[]

[ "# Llama 3 70B Instruct Storywriter\nLlama 3 70B Instruct, further finetuned on a dataset consisting of books in the fiction genre.\n\nThis was just an experiment, but it turned out well enough that I'm sharing it. The finetuning has caused a significant shift in the model's writing style, and seems to have made it more creative. There may be a slight decrease in overall intelligence.\n\nBecause this was trained on Instruct, you can use the normal Instruct chat formatting. It may also work well in raw completion mode.", "## Training details\nTrained on 4 4090s using qlora-pipe.\nDataset consists of about 800 books in the fiction genre, totaling 570 MB of raw text.\nRank 64 QLoRA trained at 8192 sequence length.", "### Evaluation metrics\n\n<img src=\"https://i.URL width=\"800\" />", "## Why no 8B?\nI tried multiple times to train this on Llama 3 8B Instruct, using a variety of hyperparameters. It never worked well. The model took a huge hit to intelligence every time, to the point of being unusable. 70B fared much better. I don't know why, maybe 8B is just too small for this type of technique, and loses too much of the instruction-tuned smarts." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Llama 3 70B Instruct Storywriter\nLlama 3 70B Instruct, further finetuned on a dataset consisting of books in the fiction genre.\n\nThis was just an experiment, but it turned out well enough that I'm sharing it. The finetuning has caused a significant shift in the model's writing style, and seems to have made it more creative. There may be a slight decrease in overall intelligence.\n\nBecause this was trained on Instruct, you can use the normal Instruct chat formatting. It may also work well in raw completion mode.", "## Training details\nTrained on 4 4090s using qlora-pipe.\nDataset consists of about 800 books in the fiction genre, totaling 570 MB of raw text.\nRank 64 QLoRA trained at 8192 sequence length.", "### Evaluation metrics\n\n<img src=\"https://i.URL width=\"800\" />", "## Why no 8B?\nI tried multiple times to train this on Llama 3 8B Instruct, using a variety of hyperparameters. It never worked well. The model took a huge hit to intelligence every time, to the point of being unusable. 70B fared much better. I don't know why, maybe 8B is just too small for this type of technique, and loses too much of the instruction-tuned smarts." ]

[ 37, 118, 49, 28, 96 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Llama 3 70B Instruct Storywriter\nLlama 3 70B Instruct, further finetuned on a dataset consisting of books in the fiction genre.\n\nThis was just an experiment, but it turned out well enough that I'm sharing it. The finetuning has caused a significant shift in the model's writing style, and seems to have made it more creative. There may be a slight decrease in overall intelligence.\n\nBecause this was trained on Instruct, you can use the normal Instruct chat formatting. It may also work well in raw completion mode.## Training details\nTrained on 4 4090s using qlora-pipe.\nDataset consists of about 800 books in the fiction genre, totaling 570 MB of raw text.\nRank 64 QLoRA trained at 8192 sequence length.### Evaluation metrics\n\n<img src=\"https://i.URL width=\"800\" />## Why no 8B?\nI tried multiple times to train this on Llama 3 8B Instruct, using a variety of hyperparameters. It never worked well. The model took a huge hit to intelligence every time, to the point of being unusable. 70B fared much better. I don't know why, maybe 8B is just too small for this type of technique, and loses too much of the instruction-tuned smarts." ]

[ "xtuner", "safetensors", "llava", "mlx", "image-text-to-text", "dataset:Lin-Chen/ShareGPT4V", "region:us" ]

[]

[]

[ "# mlx-community/llava-llama-3-8b-v1_1-8bit\nThis model was converted to MLX format from ['xtuner/llava-llama-3-8b-v1_1-transformers']() using mlx-vllm version 0.0.3.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#xtuner #safetensors #llava #mlx #image-text-to-text #dataset-Lin-Chen/ShareGPT4V #region-us \n", "# mlx-community/llava-llama-3-8b-v1_1-8bit\nThis model was converted to MLX format from ['xtuner/llava-llama-3-8b-v1_1-transformers']() using mlx-vllm version 0.0.3.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ 40, 87, 6 ]

[ "TAGS\n#xtuner #safetensors #llava #mlx #image-text-to-text #dataset-Lin-Chen/ShareGPT4V #region-us \n# mlx-community/llava-llama-3-8b-v1_1-8bit\nThis model was converted to MLX format from ['xtuner/llava-llama-3-8b-v1_1-transformers']() using mlx-vllm version 0.0.3.\nRefer to the original model card for more details on the model.## Use with mlx" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text-classification", "generated_from_trainer", "base_model:yhavinga/t5-small-24L-ccmatrix-multi", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 6", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text-classification #generated_from_trainer #base_model-yhavinga/t5-small-24L-ccmatrix-multi #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 6", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 74, 101, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text-classification #generated_from_trainer #base_model-yhavinga/t5-small-24L-ccmatrix-multi #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 6### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "pytorch", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Arara10\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #pytorch #mistral #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Arara10\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 78, 78 ]

[ "TAGS\n#transformers #pytorch #mistral #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: Arara10\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ 47 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - embracellm/sushi11_LoRA\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi11_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Pacific Combo to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #dora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - embracellm/sushi11_LoRA\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi11_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Pacific Combo to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ 72, 24, 84, 18, 25, 6, 7, 23, 17 ]

[ "TAGS\n#diffusers #tensorboard #text-to-image #diffusers-training #dora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - embracellm/sushi11_LoRA\n\n<Gallery />## Model description\n\nThese are embracellm/sushi11_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.## Trigger words\n\nYou should use a photo of Pacific Combo to trigger the image generation.## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.## Intended uses & limitations#### How to use#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "endpoints_compatible", "region:us" ]

[]

[]

[ "# savdar/snowflake-ft-camelids-l\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 20 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us \n", "# savdar/snowflake-ft-camelids-l\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 20 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ 28, 50, 30, 26, 72, 5, 5 ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us \n# savdar/snowflake-ft-camelids-l\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 20 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:## Full Model Architecture## Citing & Authors" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 55, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "endpoints_compatible", "region:us" ]

[]

[]

[ "# jjovalle99/snowflake-ft-camelids-l\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 20 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us \n", "# jjovalle99/snowflake-ft-camelids-l\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 20 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ 28, 52, 30, 26, 72, 5, 5 ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us \n# jjovalle99/snowflake-ft-camelids-l\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 20 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:## Full Model Architecture## Citing & Authors" ]

[ "meta", "llama-3", "text-generation", "en", "license:llama3", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#meta #llama-3 #text-generation #en #license-llama3 #region-us \n" ]

[ 24 ]

[ "TAGS\n#meta #llama-3 #text-generation #en #license-llama3 #region-us \n" ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

[]

[]

[ "# Tamarin_XL API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"tamarinxl\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"tamarinxl\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "# Tamarin_XL API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"tamarinxl\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"tamarinxl\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ 56, 13, 509 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n# Tamarin_XL API Inference\n\n!generated from URL## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"tamarinxl\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"tamarinxl\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "transformers", "tensorboard", "safetensors", "layoutlmv3", "token-classification", "generated_from_trainer", "base_model:microsoft/layoutlmv3-base", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #layoutlmv3 #token-classification #generated_from_trainer #base_model-microsoft/layoutlmv3-base #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 66, 99, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #layoutlmv3 #token-classification #generated_from_trainer #base_model-microsoft/layoutlmv3-base #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 1000### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

[]

[]

[ "# Booltning XL v1 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"booltning-xl-v1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"booltning-xl-v1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "# Booltning XL v1 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"booltning-xl-v1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"booltning-xl-v1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ 56, 14, 517 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n# Booltning XL v1 API Inference\n\n!generated from URL## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"booltning-xl-v1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"booltning-xl-v1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "mistral", "text-generation", "fine-tuned", "abc123", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# from_mistral_7b4-1714514853051\nDescription of the model." ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #fine-tuned #abc123 #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# from_mistral_7b4-1714514853051\nDescription of the model." ]

[ 45, 21 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #fine-tuned #abc123 #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# from_mistral_7b4-1714514853051\nDescription of the model." ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

[]

[]

[ "# Tamarin XL v1 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"tamarin-xl-v1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"tamarin-xl-v1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "# Tamarin XL v1 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"tamarin-xl-v1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"tamarin-xl-v1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ 56, 14, 517 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n# Tamarin XL v1 API Inference\n\n!generated from URL## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"tamarin-xl-v1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"tamarin-xl-v1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gptj", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gptj #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 39, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gptj #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: PythonCreate\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: PythonCreate\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 64, 80 ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: PythonCreate\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "base_model:nlpconnect/vit-gpt2-image-captioning", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #base_model-nlpconnect/vit-gpt2-image-captioning #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ 64, 103, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #base_model-nlpconnect/vit-gpt2-image-captioning #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0### Training results### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-410m", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-410m_mz-135_WordLength_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-410m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-410m_mz-135_WordLength_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 70, 58, 7, 9, 9, 4, 93, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-410m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# robust_llm_pythia-410m_mz-135_WordLength_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m on an unknown dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1### Training results### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "esm", "text-classification", "generated_from_trainer", "base_model:facebook/esm2_t12_35M_UR50D", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #esm #text-classification #generated_from_trainer #base_model-facebook/esm2_t12_35M_UR50D #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 61, 101, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #esm #text-classification #generated_from_trainer #base_model-facebook/esm2_t12_35M_UR50D #license-mit #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]