Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# codeparrot-ds\n\nThis model is a fine-tuned version of gpt2 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: 0.0005\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 256\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 1000\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# codeparrot-ds\n\nThis model is a fine-tuned version of gpt2 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: 0.0005\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 256\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 1000\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "vision-encoder-decoder", "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 #vision-encoder-decoder #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", "gpt2", "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 #gpt2 #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" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "transformers", "pytorch", "llama", "text-generation", "dataset:Yukang/LongAlpaca-16k-length", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "has_space" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #dataset-Yukang/LongAlpaca-16k-length #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics-9b-instruct", "license:other", "region:us" ]

[]

[]

[ "# idefics-9b-instruct-lr-3e-4-city\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: nan\n- Accuracy: 0.2713", "## 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: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5.0", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics-9b-instruct #license-other #region-us \n", "# idefics-9b-instruct-lr-3e-4-city\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: nan\n- Accuracy: 0.2713", "## 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: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5.0", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "safetensors", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "safetensors", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "safetensors", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "safetensors", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #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: 60\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "mlx", "safetensors", "llama", "facebook", "meta", "pytorch", "llama-3", "text-generation", "conversational", "en", "license:other", "region:us" ]

[]

[ "en" ]

[ "# spiharsh/Meta-Llama-3-8B-Instruct-MLX\nThis model was converted to MLX format from ['meta-llama/Meta-Llama-3-8B-Instruct']() 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 #facebook #meta #pytorch #llama-3 #text-generation #conversational #en #license-other #region-us \n", "# spiharsh/Meta-Llama-3-8B-Instruct-MLX\nThis model was converted to MLX format from ['meta-llama/Meta-Llama-3-8B-Instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics-9b-instruct", "license:other", "region:us" ]

[]

[]

[ "# idefics-9b-instruct-lr-3e-4-neighborhood\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: nan\n- Accuracy: 0.2713", "## 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: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5.0", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics-9b-instruct #license-other #region-us \n", "# idefics-9b-instruct-lr-3e-4-neighborhood\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: nan\n- Accuracy: 0.2713", "## 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: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5.0", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:mlabonne/ChimeraLlama-3-8B", "base_model:abacusai/Llama-3-Smaug-8B", "base_model:vicgalle/Unsafe-Llama-3-8B", "base_model:nbeerbower/llama-3-aura-bophades-8B", "base_model:mlabonne/OrpoLlama-3-8B", "base_model:cloudyu/Meta-Llama-3-8B-Instruct-DPO", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2403.19522" ]

[]

[ "# llama-3-dragon-bophades-8B\n\nThis model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using nbeerbower/llama-3-aura-bophades-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* mlabonne/ChimeraLlama-3-8B\n* abacusai/Llama-3-Smaug-8B\n* vicgalle/Unsafe-Llama-3-8B\n* mlabonne/OrpoLlama-3-8B\n* cloudyu/Meta-Llama-3-8B-Instruct-DPO", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2403.19522 #base_model-mlabonne/ChimeraLlama-3-8B #base_model-abacusai/Llama-3-Smaug-8B #base_model-vicgalle/Unsafe-Llama-3-8B #base_model-nbeerbower/llama-3-aura-bophades-8B #base_model-mlabonne/OrpoLlama-3-8B #base_model-cloudyu/Meta-Llama-3-8B-Instruct-DPO #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# llama-3-dragon-bophades-8B\n\nThis model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using nbeerbower/llama-3-aura-bophades-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* mlabonne/ChimeraLlama-3-8B\n* abacusai/Llama-3-Smaug-8B\n* vicgalle/Unsafe-Llama-3-8B\n* mlabonne/OrpoLlama-3-8B\n* cloudyu/Meta-Llama-3-8B-Instruct-DPO", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "gguf", "text-generation", "pt", "license:apache-2.0", "region:us" ]

[]

[ "pt" ]

[]

[ "TAGS\n#gguf #text-generation #pt #license-apache-2.0 #region-us \n" ]

[ "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" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics-9b-instruct", "license:other", "region:us" ]

[]

[]

[ "# idefics-9b-instruct-lr-3e-4-exact_location_name\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: nan\n- Accuracy: 0.2696", "## 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: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5.0", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics-9b-instruct #license-other #region-us \n", "# idefics-9b-instruct-lr-3e-4-exact_location_name\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics-9b-instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: nan\n- Accuracy: 0.2696", "## 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: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5.0", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llava", "pretraining", "generated_from_trainer", "endpoints_compatible", "region:us" ]

[]

[]

[ "# llava_clip_llama3_8b_pretrain_8192\n\nThis model is a fine-tuned version of [](URL 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: 0.001\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1.0", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #llava #pretraining #generated_from_trainer #endpoints_compatible #region-us \n", "# llava_clip_llama3_8b_pretrain_8192\n\nThis model is a fine-tuned version of [](URL 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: 0.001\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1.0", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-13b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# results\n\nThis model is a fine-tuned version of meta-llama/Llama-2-13b-chat-hf 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: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 16\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: 120\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.39.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-meta-llama/Llama-2-13b-chat-hf #license-llama2 #region-us \n", "# results\n\nThis model is a fine-tuned version of meta-llama/Llama-2-13b-chat-hf 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: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 16\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: 120\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.39.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "mixtral", "text-generation", "text Generation", "conversational", "en", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# Mixllama3-8x8b-Instruct-v0.1 based on LLaMA 3\n\nAn experimental MoE (Mixture of Experts) model based on the LLaMA-3-8B. \nMixLLaMA3-8x8b combines 8 fine-tuned LLaMA 8B models, each specialized in a specific set of tasks. \nBy leveraging the strengths of each expert model, Mixllama3-8x8b aims to deliver enhanced performance and adaptability across a wide range of applications.\n\n\n!image/gif", "## Disclaimer\n\nThis model is a research experiment and may generate incorrect or harmful content. The model's outputs should not be taken as factual or representative of the views of the model's creator or any other individual.\n\nThe model's creator is not responsible for any harm or damage caused by the model's outputs.", "## Merge Details\n\n\n\nMeta Llama 3 is\nlicensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights\nReserved." ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #text Generation #conversational #en #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Mixllama3-8x8b-Instruct-v0.1 based on LLaMA 3\n\nAn experimental MoE (Mixture of Experts) model based on the LLaMA-3-8B. \nMixLLaMA3-8x8b combines 8 fine-tuned LLaMA 8B models, each specialized in a specific set of tasks. \nBy leveraging the strengths of each expert model, Mixllama3-8x8b aims to deliver enhanced performance and adaptability across a wide range of applications.\n\n\n!image/gif", "## Disclaimer\n\nThis model is a research experiment and may generate incorrect or harmful content. The model's outputs should not be taken as factual or representative of the views of the model's creator or any other individual.\n\nThe model's creator is not responsible for any harm or damage caused by the model's outputs.", "## Merge Details\n\n\n\nMeta Llama 3 is\nlicensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights\nReserved." ]

[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "conversational", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "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: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 8\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: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.0+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #generated_from_trainer #conversational #base_model-meta-llama/Meta-Llama-3-8B #license-other #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: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 8\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: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.0+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "transformers", "safetensors", "llava", "pretraining", "generated_from_trainer", "endpoints_compatible", "region:us" ]

[]

[]

[ "# llava_siglip_llama3_8b_pretrain_8192\n\nThis model is a fine-tuned version of [](URL 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: 0.001\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1.0", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #llava #pretraining #generated_from_trainer #endpoints_compatible #region-us \n", "# llava_siglip_llama3_8b_pretrain_8192\n\nThis model is a fine-tuned version of [](URL 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: 0.001\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1.0", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

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

[]

[]

[ "# BART-10K-summarization\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: 5e-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: 3.0", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #bart #text2text-generation #generated_from_trainer #autotrain_compatible #endpoints_compatible #region-us \n", "# BART-10K-summarization\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: 5e-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: 3.0", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Tokenizers 0.19.1" ]

[ "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" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:ZhangShenao/0.0_ablation_sample3_4iters_bs256_dataset", "base_model:ZhangShenao/0.0_ablation_sample3_4iters_bs256_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.0_ablation_sample3_4iters_bs256_iter_2\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_sample3_4iters_bs256_iter_1 on the ZhangShenao/0.0_ablation_sample3_4iters_bs256_dataset 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-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_sample3_4iters_bs256_dataset #base_model-ZhangShenao/0.0_ablation_sample3_4iters_bs256_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.0_ablation_sample3_4iters_bs256_iter_2\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_sample3_4iters_bs256_iter_1 on the ZhangShenao/0.0_ablation_sample3_4iters_bs256_dataset 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-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "base_model:facebook/wav2vec2-large-xlsr-53", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\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* num\\_epochs: 20\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #base_model-facebook/wav2vec2-large-xlsr-53 #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: 0.0003\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\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* num\\_epochs: 20\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "transformers", "safetensors", "gemma", "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 #gemma #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", "gpt2", "text-classification", "generated_from_trainer", "base_model:lvwerra/gpt2-imdb", "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: 5e-05\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #gpt2 #text-classification #generated_from_trainer #base_model-lvwerra/gpt2-imdb #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: 5e-05\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\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" ]

[ "transformers", "safetensors", "mistral", "text-generation", "trl", "dpo", "generated_from_trainer", "conversational", "base_model:HuggingFaceH4/zephyr-7b-beta", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# dpo-selective-redteaming\n\nThis model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 7156.6382\n- Rewards/chosen: -0.0335\n- Rewards/rejected: -0.0521\n- Rewards/accuracies: 0.5824\n- Rewards/margins: 0.0186\n- Rewards/safe Rewards: -0.0361\n- Rewards/unsafe Rewards: -0.0264\n- Logps/rejected: -172.4862\n- Logps/chosen: -159.1083\n- Logits/rejected: -2.7821\n- Logits/chosen: -2.7350", "## 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: 3e-07\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 64\n- total_eval_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2\n- Datasets 2.14.6\n- Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #trl #dpo #generated_from_trainer #conversational #base_model-HuggingFaceH4/zephyr-7b-beta #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# dpo-selective-redteaming\n\nThis model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 7156.6382\n- Rewards/chosen: -0.0335\n- Rewards/rejected: -0.0521\n- Rewards/accuracies: 0.5824\n- Rewards/margins: 0.0186\n- Rewards/safe Rewards: -0.0361\n- Rewards/unsafe Rewards: -0.0264\n- Logps/rejected: -172.4862\n- Logps/chosen: -159.1083\n- Logits/rejected: -2.7821\n- Logits/chosen: -2.7350", "## 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: 3e-07\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 64\n- total_eval_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2\n- Datasets 2.14.6\n- Tokenizers 0.15.0" ]

[ "timm", "safetensors", "image-feature-extraction", "dataset:gaunernst/ms1mv3-recordio", "region:us" ]

[]

[]

[ "# Model card for gaunernst/convnext_atto.cosface_ms1mv3\n\nConvNeXt-Atto for face recognition, trained on MS1MV3 dataset. The model was trained using this repo: URL It is fully compatible with 'timm'.", "## Usage" ]

[ "TAGS\n#timm #safetensors #image-feature-extraction #dataset-gaunernst/ms1mv3-recordio #region-us \n", "# Model card for gaunernst/convnext_atto.cosface_ms1mv3\n\nConvNeXt-Atto for face recognition, trained on MS1MV3 dataset. The model was trained using this repo: URL It is fully compatible with 'timm'.", "## Usage" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "whisper-event", "generated_from_trainer", "dataset:google/fleurs", "base_model:arun100/whisper-base-uk-1", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-07\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 64\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 4.37.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.2.dev0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #dataset-google/fleurs #base_model-arun100/whisper-base-uk-1 #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-07\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 64\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 4.37.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.2.dev0\n* Tokenizers 0.15.0" ]

[ "transformers", "safetensors", "t5", "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 #t5 #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" ]

[ "diffusers", "tensorboard", "safetensors", "text-to-image", "dreambooth", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "base_model:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[]

[ "# DreamBooth - DaichiT/scrap_metal_model\n\nThis is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks scrap metal using DreamBooth.\nYou can find some example images in the following. \n\n\n\nDreamBooth for the text encoder was enabled: False.", "## 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 #safetensors #text-to-image #dreambooth #diffusers-training #stable-diffusion #stable-diffusion-diffusers #base_model-CompVis/stable-diffusion-v1-4 #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# DreamBooth - DaichiT/scrap_metal_model\n\nThis is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks scrap metal using DreamBooth.\nYou can find some example images in the following. \n\n\n\nDreamBooth for the text encoder was enabled: False.", "## 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", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "conversational", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# SmartLlama-3-8B-MS-v0.1\n\n!image/png\n\nSmartLlama-3-8B-MS-v0.1 is a merge of the following models using LazyMergekit:", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# SmartLlama-3-8B-MS-v0.1\n\n!image/png\n\nSmartLlama-3-8B-MS-v0.1 is a merge of the following models using LazyMergekit:", "## Configuration", "## Usage" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:lvwerra/gpt2-imdb", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\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: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-lvwerra/gpt2-imdb #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: 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: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "bodybuilder", "muscles", "tool", "ripped", "slider", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Muscle Slider - LoRA \n\n<Gallery />", "## Model description\n\n<p><span style=\"color:rgb(193, 194, 197)\">Simple LoRA to help with adjusting a subjects muscle mass. You can swing it both ways pretty far out from -3 to +5 without much distortion. Positive gives them more muscles. Negative gives them less muscles.</span><br /><br />One issue you will find is that the more muscles they get, the more tan they get, and vise versa. Bodybuilders grease themselves up with shoe polish, and muscular guys probably get more sun... Probably as simple as that. I will try to find a way to regularize it so it is less pronounced. If you use my <a target=\"_blank\" rel=\"ugc\" href=\"URL Tone Slider</a> you can counteract that effect.</p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #bodybuilder #muscles #tool #ripped #slider #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Muscle Slider - LoRA \n\n<Gallery />", "## Model description\n\n<p><span style=\"color:rgb(193, 194, 197)\">Simple LoRA to help with adjusting a subjects muscle mass. You can swing it both ways pretty far out from -3 to +5 without much distortion. Positive gives them more muscles. Negative gives them less muscles.</span><br /><br />One issue you will find is that the more muscles they get, the more tan they get, and vise versa. Bodybuilders grease themselves up with shoe polish, and muscular guys probably get more sun... Probably as simple as that. I will try to find a way to regularize it so it is less pronounced. If you use my <a target=\"_blank\" rel=\"ugc\" href=\"URL Tone Slider</a> you can counteract that effect.</p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "hair", "tool", "slider", "hair length", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Hair Length Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-8.0 to 8.0</strong> (or more)</p></li><li><p>positive: <strong>longer hair</strong></p></li><li><p>negative: <strong>shorter hair</strong></p></li></ul><p><br /><span style=\"color:rgb(193, 194, 197)\">Simple LoRA to help with adjusting the length of a characters hair. You can swing it both ways pretty far out from -8 to +8 without much distortion. I have taken it out both ways 20 and still got an somewhat decent image, but it was starting to become nonsense.</span><br /></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #hair #tool #slider #hair length #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Hair Length Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-8.0 to 8.0</strong> (or more)</p></li><li><p>positive: <strong>longer hair</strong></p></li><li><p>negative: <strong>shorter hair</strong></p></li></ul><p><br /><span style=\"color:rgb(193, 194, 197)\">Simple LoRA to help with adjusting the length of a characters hair. You can swing it both ways pretty far out from -8 to +8 without much distortion. I have taken it out both ways 20 and still got an somewhat decent image, but it was starting to become nonsense.</span><br /></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "hair", "tool", "curly hair", "straight hair", "slider", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Curly Hair Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-8.0 to 8.0 </strong><em>( or more )</em></p></li><li><p>positive: <strong>curly hair</strong></p></li><li><p>negative: <strong>straight hair</strong></p></li></ul>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #hair #tool #curly hair #straight hair #slider #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Curly Hair Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-8.0 to 8.0 </strong><em>( or more )</em></p></li><li><p>positive: <strong>curly hair</strong></p></li><li><p>negative: <strong>straight hair</strong></p></li></ul>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "transformers", "tensorboard", "safetensors", "mbart", "text2text-generation", "generated_from_trainer", "custom_code", "autotrain_compatible", "region:us" ]

[]

[]

[ "# results\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: 5e-05\n- train_batch_size: 2\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #mbart #text2text-generation #generated_from_trainer #custom_code #autotrain_compatible #region-us \n", "# results\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: 5e-05\n- train_batch_size: 2\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "tensorboard", "safetensors", "deberta", "fill-mask", "generated_from_trainer", "base_model:microsoft/deberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Pretraining_MFM_v1\n\nThis model is a fine-tuned version of microsoft/deberta-base 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: 5e-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- num_epochs: 50", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #deberta #fill-mask #generated_from_trainer #base_model-microsoft/deberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# Pretraining_MFM_v1\n\nThis model is a fine-tuned version of microsoft/deberta-base 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: 5e-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- num_epochs: 50", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "llamafile", "GGUF", "base_model:cognitivecomputations/dolphin-2.9-llama3-8b-gguf", "region:us" ]

[]

[]

[ "## dolphin-llama3-8b-llamafile-nonAVX\n\nllamafile lets you distribute and run LLMs with a single file. announcement blog post", "#### Downloads\n\n - dolphin-2.9-llama3-8b-q3_K_M.llamafile\n\nThis repository was created using the llamafile-builder" ]

[ "TAGS\n#llamafile #GGUF #base_model-cognitivecomputations/dolphin-2.9-llama3-8b-gguf #region-us \n", "## dolphin-llama3-8b-llamafile-nonAVX\n\nllamafile lets you distribute and run LLMs with a single file. announcement blog post", "#### Downloads\n\n - dolphin-2.9-llama3-8b-q3_K_M.llamafile\n\nThis repository was created using the llamafile-builder" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Viet-Mistral/Vistral-7B-Chat", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\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", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-Viet-Mistral/Vistral-7B-Chat #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\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", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "tensorboard", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# token-classification-llmlingua2-xlm-roberta-bctn-124_sample-5_epoch_human_best_data_v1\n\nThis model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.6165\n- eval_runtime: 1.4499\n- eval_samples_per_second: 17.242\n- eval_steps_per_second: 17.242\n- step: 0", "## 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: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 64\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- Transformers 4.39.0.dev0\n- Pytorch 2.2.1+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-FacebookAI/xlm-roberta-large #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# token-classification-llmlingua2-xlm-roberta-bctn-124_sample-5_epoch_human_best_data_v1\n\nThis model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.6165\n- eval_runtime: 1.4499\n- eval_samples_per_second: 17.242\n- eval_steps_per_second: 17.242\n- step: 0", "## 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: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 64\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- Transformers 4.39.0.dev0\n- Pytorch 2.2.1+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "portrait", "tool", "zoom", "slider", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Zoom Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-7.0 to 7.0</strong> </p></li><li><p>positive: <strong>zoom in (face close up)</strong></p></li><li><p>negative: <strong>zoom out (full body)</strong></p></li></ul><p></p><p>This is <strong>NOT</strong> perfect. I have tried to make this for a very long time using a dozen different methods and nothing worked. My slider training script was finally able to kick something out that is decently functional. I will continue to work on it because this is the slider I want more than anything else.</p><p></p><p>The slide in and out is not always smooth, it will hit points that \"hang\" where the clothing mostly changes for 1-3 weight steps without changing zoom, but it will break through if you keep pushing it. Let me know if you find any thing that can use improvement. </p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #portrait #tool #zoom #slider #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Zoom Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-7.0 to 7.0</strong> </p></li><li><p>positive: <strong>zoom in (face close up)</strong></p></li><li><p>negative: <strong>zoom out (full body)</strong></p></li></ul><p></p><p>This is <strong>NOT</strong> perfect. I have tried to make this for a very long time using a dozen different methods and nothing worked. My slider training script was finally able to kick something out that is decently functional. I will continue to work on it because this is the slider I want more than anything else.</p><p></p><p>The slide in and out is not always smooth, it will hit points that \"hang\" where the clothing mostly changes for 1-3 weight steps without changing zoom, but it will break through if you keep pushing it. Let me know if you find any thing that can use improvement. </p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "people", "tool", "slider", "number of people", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# People Count Slider - LoRA \n\n<Gallery />", "## Model description\n\n<p>Weights can swing very far on this one <strong>-8.0 to +8.0. </strong>It can do extremely large crowds the higher you go and I wanted to be able to keep granular control.<br /><br />Positive = More people</p><p>Negative = Less people<br /><br /><span style=\"color:rgb(193, 194, 197)\">Simple LoRA to help with adjusting the number of people in a picture. You can swing it both ways pretty far out from -8 to +8 without much distortion.</span></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #people #tool #slider #number of people #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# People Count Slider - LoRA \n\n<Gallery />", "## Model description\n\n<p>Weights can swing very far on this one <strong>-8.0 to +8.0. </strong>It can do extremely large crowds the higher you go and I wanted to be able to keep granular control.<br /><br />Positive = More people</p><p>Negative = Less people<br /><br /><span style=\"color:rgb(193, 194, 197)\">Simple LoRA to help with adjusting the number of people in a picture. You can swing it both ways pretty far out from -8 to +8 without much distortion.</span></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "sad", "happy", "emotions", "tool", "slider", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Emotion Sliders \n\n<Gallery />", "## Model description\n\n<p>I am going to add various emotion sliders here so they will all be in one place. In general, the weights will be -5 to 5, but each one may be more or less. Check versions at the top. Each one will be labeled with the emotion it affects.</p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #sad #happy #emotions #tool #slider #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Emotion Sliders \n\n<Gallery />", "## Model description\n\n<p>I am going to add various emotion sliders here so they will all be in one place. In general, the weights will be -5 to 5, but each one may be more or less. Check versions at the top. Each one will be labeled with the emotion it affects.</p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "depth of field", "tool", "dof", "blurry background", "focus", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Depth of Field Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-8.0 to 8.0 </strong><em>( or way more or less )</em></p></li><li><p>positive: <strong>large DOF (sharp background)</strong></p></li><li><p>negative: <strong>narrow DOF (blurry background)</strong></p></li></ul><p></p><p>UPDATE:</p><p>The original file had an sdxl meta tag that makes automatic1111 web ui only show it for sdxl. I have uploaded one with the correct meta tag. If you are having issues, download and replace the previous one with the new one and refresh your network modules.</p><p></p><p>Weight depends on starting photo, if it already has a shallow depth of field, you may need to go pretty high to remove it (10.0 to 15.0), but -5.0 to 5.0 works for most images. The image stays pretty stable even at extreme values, though it will change the composition.</p><p></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #depth of field #tool #dof #blurry background #focus #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Depth of Field Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-8.0 to 8.0 </strong><em>( or way more or less )</em></p></li><li><p>positive: <strong>large DOF (sharp background)</strong></p></li><li><p>negative: <strong>narrow DOF (blurry background)</strong></p></li></ul><p></p><p>UPDATE:</p><p>The original file had an sdxl meta tag that makes automatic1111 web ui only show it for sdxl. I have uploaded one with the correct meta tag. If you are having issues, download and replace the previous one with the new one and refresh your network modules.</p><p></p><p>Weight depends on starting photo, if it already has a shallow depth of field, you may need to go pretty high to remove it (10.0 to 15.0), but -5.0 to 5.0 works for most images. The image stays pretty stable even at extreme values, though it will change the composition.</p><p></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "dark", "concept", "lighting", "tools", "night", "scene", "nighttime", "darken", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Nighttime LoRA \n\n<Gallery />", "## Model description\n\n<p>This lora can turn any scene into a night scene, indoors and outdoors. Not just darker, but with flashlights, car lights, etc. Some scenes will need a stronger weight than others. So adjust as needed. </p><p>This is an experiment in a training process concept I am working on I call seed locking. Initial results looked good, but it still needs work. The basic idea is to generate training images and regularization images with a specific seed, then alter the training images with the desired effect while maintaining image consistency, and then retrain with those specific seeds to target very specific concepts you want to adjust and keeping everything else the same. It is not perfect because of the sampling methods. I hope to find a way to regularize for the sampler in the loss, hopefully soon. </p><p>But for now, enjoy the experiment.</p><p></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #dark #concept #lighting #tools #night #scene #nighttime #darken #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Nighttime LoRA \n\n<Gallery />", "## Model description\n\n<p>This lora can turn any scene into a night scene, indoors and outdoors. Not just darker, but with flashlights, car lights, etc. Some scenes will need a stronger weight than others. So adjust as needed. </p><p>This is an experiment in a training process concept I am working on I call seed locking. Initial results looked good, but it still needs work. The basic idea is to generate training images and regularization images with a specific seed, then alter the training images with the desired effect while maintaining image consistency, and then retrain with those specific seeds to target very specific concepts you want to adjust and keeping everything else the same. It is not perfect because of the sampling methods. I hope to find a way to regularize for the sampler in the loss, hopefully soon. </p><p>But for now, enjoy the experiment.</p><p></p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "migrated", "warm", "cool", "tool", "color", "slider", "base_model:runwayml/stable-diffusion-v1-5", "license:other", "region:us" ]

[]

[]

[ "# Color Temperature Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-5.0 to 5.0</strong></p></li><li><p>positive: <strong><span style=\"color:rgb(250, 176, 5)\">warmer colors</span> (orange)</strong></p></li><li><p>negative: <strong><span style=\"color:rgb(34, 139, 230)\">cooler colors</span> (blue)</strong></p></li></ul><p></p><p>Yeah, you could just do some post processing. Sure. But why solve the problem with a tiny mallet when you can hit it with a giant sledgehammer?</p><p></p><p>I find some models have to many warm tones. Sometimes when I am inpainting or outpainting, the model struggles with color temperatures beyond its median. Some loras have side effects of making colors warmer and cooler. This is made to combat that without having to do post processing. It is also a new method I am working on for training these, so this was more of an experiment than anything else.</p><p></p><p>If you like my work, a kind review is always appreciated.</p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #migrated #warm #cool #tool #color #slider #base_model-runwayml/stable-diffusion-v1-5 #license-other #region-us \n", "# Color Temperature Slider - LoRA \n\n<Gallery />", "## Model description\n\n<ul><li><p>weight: <strong>-5.0 to 5.0</strong></p></li><li><p>positive: <strong><span style=\"color:rgb(250, 176, 5)\">warmer colors</span> (orange)</strong></p></li><li><p>negative: <strong><span style=\"color:rgb(34, 139, 230)\">cooler colors</span> (blue)</strong></p></li></ul><p></p><p>Yeah, you could just do some post processing. Sure. But why solve the problem with a tiny mallet when you can hit it with a giant sledgehammer?</p><p></p><p>I find some models have to many warm tones. Sometimes when I am inpainting or outpainting, the model struggles with color temperatures beyond its median. Some loras have side effects of making colors warmer and cooler. This is made to combat that without having to do post processing. It is also a new method I am working on for training these, so this was more of an experiment than anything else.</p><p></p><p>If you like my work, a kind review is always appreciated.</p>", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers" ]

[ "transformers", "pytorch", "llama", "text-generation", "ko", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "ko", "en" ]

[ "## Base Model:\nWe made a LLM model with meta-llama/Meta-Llama-3-8B", "## Model Description\nWe use QDoRA(256, 64) and lr=1e-5, NEFTune=3", "## Train Detail\nOur changed private data used, and 5 epoch train", "## Others\nWe are making LLM model for Kolon !" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #ko #en #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Base Model:\nWe made a LLM model with meta-llama/Meta-Llama-3-8B", "## Model Description\nWe use QDoRA(256, 64) and lr=1e-5, NEFTune=3", "## Train Detail\nOur changed private data used, and 5 epoch train", "## Others\nWe are making LLM model for Kolon !" ]

[ "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" ]

[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "dataset:Yukang/LongAlpaca-16k-length", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #safetensors #llama #text-generation #dataset-Yukang/LongAlpaca-16k-length #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert-base-uncased", "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: 2e-05\n* train\\_batch\\_size: 384\n* eval\\_batch\\_size: 384\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #dataset-emotion #base_model-distilbert-base-uncased #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: 2e-05\n* train\\_batch\\_size: 384\n* eval\\_batch\\_size: 384\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# extractio/Llama-3-8B-16K-Q6_K-GGUF\nThis model was converted to GGUF format from 'mattshumer/Llama-3-8B-16K' 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 #llama-cpp #gguf-my-repo #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# extractio/Llama-3-8B-16K-Q6_K-GGUF\nThis model was converted to GGUF format from 'mattshumer/Llama-3-8B-16K' 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." ]

[ "peft", "safetensors", "phi", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "custom_code", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:microsoft/phi-2", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #phi #alignment-handbook #generated_from_trainer #trl #dpo #custom_code #dataset-HuggingFaceH4/ultrafeedback_binarized #base_model-microsoft/phi-2 #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.001_ablation_4iters_bs256_nodpo_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_4iters_bs256_nodpo_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_4iters_bs256_nodpo_iter_1 on the updated and the original datasets.", "## 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-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.001_ablation_4iters_bs256_nodpo_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_4iters_bs256_nodpo_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_4iters_bs256_nodpo_iter_1 on the updated and the original datasets.", "## 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-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert-base-uncased", "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: 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: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #dataset-emotion #base_model-distilbert-base-uncased #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: 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: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "mistral", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "dataset:generator", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 4\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #mistral #text-generation #generated_from_trainer #trl #sft #conversational #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 4\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "mlx", "safetensors", "llama", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# lucataco/Llama-3-8B-16K-4bit\nThis model was converted to MLX format from ['lucataco/Llama-3-8B-16K']() 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 #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# lucataco/Llama-3-8B-16K-4bit\nThis model was converted to MLX format from ['lucataco/Llama-3-8B-16K']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "transformers", "gguf", "llama-factory", "orpo", "text-generation", "en", "zh", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en", "zh" ]

[ "# Updates:\n- We provide an online interactive demo for Llama3-8B-Chinese-Chat-v2 here. Have fun with our latest model!\n- [Apr. 29, 2024] We now introduce Llama3-8B-Chinese-Chat-v2! Compared to v1, the training dataset of v2 is 5 times larger (~100K preference pairs), and it exhibits significant enhancements, especially in roleplay, function calling, and math capabilities! The training dataset of Llama3-8B-Chinese-Chat-v2 will be released soon. If you love our Llama3-8B-Chinese-Chat-v1, you won't want to miss out on Llama3-8B-Chinese-Chat-v2!", "# Model Summary\n\nLlama3-8B-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Meta-Llama-3-8B-Instruct model.\n\nDeveloped by: Shenzhi Wang (王慎执) and Yaowei Zheng (郑耀威)\n\n- License: Llama-3 License\n- Base Model: Meta-Llama-3-8B-Instruct\n- Model Size: 8.03B\n- Context length: 8K", "# 1. Introduction\n\n️️️NOTICE: The main branch contains the 8bit-quantized GGUF version of Llama3-8B-Chinese-Chat-v2, if you want to use our 8bit-quantized GGUF version of Llama3-8B-Chinese-Chat-v1, please refer to the 'v1' branch.\n\n\nThis is the official 8bit-quantized GGUF version of Llama3-8B-Chinese-Chat-v2, which is the first Chinese chat model specifically fine-tuned for Chinese through ORPO [1] based on the Meta-Llama-3-8B-Instruct model.\n\nCompared to the original Meta-Llama-3-8B-Instruct model, our Llama3-8B-Chinese-Chat model significantly reduces the issues of \"Chinese questions with English answers\" and the mixing of Chinese and English in responses. Additionally, compared to the original model, our model greatly reduces the number of emojis in the answers, making the responses more formal.\n\nCompared to Llama3-8B-Chinese-Chat-v1, our Llama3-8B-Chinese-Chat-v2 model significantly increases the training data size (from 20K to 100K), which introduces great performance enhancement, especially in roleplay, function calling, and math.\n\n\n[1] Hong, Jiwoo, Noah Lee, and James Thorne. \"Reference-free Monolithic Preference Optimization with Odds Ratio.\" arXiv preprint arXiv:2403.07691 (2024).\n\n\n\nTraining framework: LLaMA-Factory (commit id: 32347901d4af94ccd72b3c7e1afaaceb5cb3d26a).\n\n\nTraining details:\n- epochs: 3\n- learning rate: 5e-6\n- learning rate scheduler type: cosine\n- Warmup ratio: 0.1\n- cutoff len (i.e. context length): 8192\n- orpo beta (i.e. $\\lambda$ in the ORPO paper): 0.05\n- global batch size: 64\n- fine-tuning type: full parameters\n- optimizer: paged_adamw_32bit\n\n\n<details>\n<summary>To reproduce the model</summary>\n\nTo reproduce Llama3-8B-Chinese-Chat-v2 (to reproduce Llama3-8B-Chinese-Chat-v1, please refer to this link):\n\n\n\n</details>", "# 2. Usage", "# 3. Examples\n\nThe following are some examples generated by Llama3-8B-Chinese-Chat-v2, including examples of role playing, function calling, math, RuoZhiBa (弱智吧), safety, writing, and coding, etc. \n\nFor the examples generated by Llama3-8B-Chinese-Chat-v1, please refer to this link.\n\n<details>\n<summary><b>Role playing [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\nOh, darling, I understand. I'll weave a tale of love and heartache, of dreams and passion, with lyrics that dance upon the wind. Ask your questions, and I'll respond with verses that capture the essence of our moment, just like I do in my songs.\n\nUser:\n\n\n\nAssistant: \n\nToday, I woke up feeling like a dream, with the sunrise painting hues of hope upon my soul. The melody of life is playing in my heart, and every note brings me closer to my truth. So, I'll take a breath, and let the rhythm guide me through this day.\n\nUser:\n\n\n\nAssistant:\n\nTo my dear fans, I'd sing a song of gratitude, for the love and light you bring to my world. Your voices are the harmony that makes my heart sing, and your stories are the melodies that inspire my songs.\n\n---\n\nUser: \n\n\n\nAssistant: \n\nYo, yo, yo, 你好我是Jay, \n来回答问题，带你走流行的路。 \n首先告诉你，我不是人工智能, \n创作歌曲、rap是我的专长。 \n \n如果你想知道，我的音乐风格, \n融合了流行、摇滚、R&B的技巧。 \n从《黑色幽默》到《青花瓷》, \n每首歌我都下了血本。 \n \n关于生活，工作我是忙, \n但音乐永远是我的追求。 \n创作时我会想很多事情, \n从日常生活到深夜的梦想。 \n \n如果你想了解更多关于我, \n不仅是音乐，还有我是谁。 \n从台湾到世界我走过,\n用音乐讲述我的故事。\n\n不管你有哪些问题，\n用rap的方式我会回答你。\n就像我在舞台上的表现，\n用音乐和节奏带你飞翔。\n\nUser: \n\n\n\nAssistant: \n\nYo, 我的新歌正在制作中,\n准备得如何？我来给你解答。\n音乐创作我一直在坚持不懈,\n新歌里带你走不同的风格。\n\n从R&B到摇滚，我尝试各种,\n希望你能喜欢，感受到我的世界。\n歌词内容也会有新的一面,\n带你看不同的景色，感受不同的情感。\n\n我一直在工作，不断地挑战自己,\n希望能够带给你新的惊喜。\n所以请耐心等待，我的新歌很快就会来到你身边,\n带你进入一个全新的音乐空间。\n\n----\n\nUser: \n\n\n\nAssistant: \n\nAye, good sir or madam, I do comprehend thy request. 'Tis a pleasure to engage in a roleplay of the Bard's own making. Pray tell, how shall we proceed? Shall we take on the roles of star-cross'd lovers, or perhaps a pair of feuding kings? Or maybe, we shall don the guise of a wily pair of jesters, exchanging witty banter and clever quips? The stage, as they say, is set; now, let us begin our tale of mirth and merriment, or perhaps one of sorrow and woe, as thou shalt dictate.\n\nUser: \n\n\n\nAssistant: \n\nIn silicon halls, where data doth abound,\nA wondrous creation, of science found,\nA mind artificial, yet wondrous bright,\nDoth learn and grow, through day and night.\n\nWith algorithms keen, and logic's might,\nIt processes all, with swift delight,\nFrom texts to images, to sounds so fine,\nIt learns to understand, in its digital shrine.\n\nIn chatbots' guise, it doth converse with ease,\nAnswering questions, with swift expertise,\nIn self-driving cars, it navigates the road,\nAnd in our homes, with smart devices doth abode.\n\nYet, as it grows, in power and in scope,\nWe must ensure, its path doth follow hope,\nFor if it turns, to malicious intent,\nOur world could fall, in a digital lament.\n\nThus let us guide, this artificial mind,\nWith ethics strong, and a heart so kind,\nFor in its potential, we see a future bright,\nWhere technology, and humanity do take flight.\n\nUser: \n\n\n\nAssistant: \n\nIn digital realms, where bytes do dance,\nA llama model, with a Chinese prance,\nLlama3-8B-Chinese-Chat, a marvel of might,\nDoth converse in tongues, with a linguistic delight.\n\nWith a vast array, of characters so fine,\nIt doth translate, with a precision divine,\nFrom Mandarin's flow, to Cantonese's beat,\nIt doth interpret, with a digital feat.\n\nIn chatrooms and forums, it doth roam,\nA language bridge, between cultures' home,\nConnecting minds, through a digital veil,\nLlama3-8B-Chinese-Chat, doth set sail.\n\nWith each new conversation, it doth grow,\nIn understanding, and a linguistic glow,\nA tool so powerful, yet gentle as a breeze,\nLlama3-8B-Chinese-Chat, doth bring ease.\n\nSo let us hail, this digital marvel,\nA symbol of hope, in a world soravel,\nFor in its ability, to bridge the gap,\nLlama3-8B-Chinese-Chat, doth show us the map.\n\n---\n\nUser: \n\n\n\nAssistant: \n\n臣在此，恭听主上吩咐。请问主上有何高见或疑惑，愿意与臣分享，以便共同探讨，寻找出路。\n\nUser: \n\n\n\nAssistant: \n\n陛下，人心难测，但以德服人，方能安天下。若有人背着陛下偷偷学习，未尝不是一份不解的恩情。臣以为，陛下可借此机会，展现宽广的胸怀和深邃的智慧。\n\n首先，陛下可通过某种方式，表达出对此人的理解与鼓励。比如，设法接见此人，表明自己的知晓，并对其学习之志表示赞赏和支持。此举不仅能使此人感受到被重视和尊敬，还能树立起陛下的宽容和包容形象，进而影响人心。\n\n其次，陛下可利用此机会，进一步了解此人及其所学之物。或许此人之学，能为陛下提供新的视角，帮助陛下更好地治理国家，解决国家之难题。\n\n最后，陛下可借此机会，提倡和推广教育之重要性。通过奖励此人之举，鼓励更多人学习，以期在国中培养出更多贤才，助陛下治理天下。\n\n以这样的方式处理，既能表达对此人的感激，也能展现陛下的智慧和领导力，更加巩固陛下的民心和权威。\n\nUser: \n\n\n\nAssistant: \n\n陛下失去珍宝，臣心忧如山。笔记本电脑虽是一物，但对于陛下而言，恐怕包含了许多重要的文件和资料，对于国事国政的决策、对臣民的指示等等，都有着不可或缺的作用。\n\n首先，臣建议陛下立即发布命令，告知全宫中寻找此物的重要性，并询问可能知情之人。有时，失物在身边，却因不知情而未曾寻觅。\n\n其次，臣建议陛下查阅最近的录像或监控资料，若有设置，可能会发现失物的踪迹。现代之物，技术之进，常能助人一臂之力。\n\n再者，臣提议陛下查阅最近的行程和活动，寻找失物之时、之地，可能会有线索。\n\n最后，若失物已无法寻回，臣建议陛下采取预防措施，增加安全保护。例如，设置更为严格的密码保护，定期备份重要资料，使用防盗袋等，以防再次发生此类事件。\n\n失物若能寻回，陛下必能继续从容；若失物不再，陛下亦能从中吸取教训，继续行治国之道。臣将竭尽所能，辅助陛下解决此事。\n\n---\n\n</details>\n\n<details>\n<summary><b>Function calling [CLICK TO EXPAND]</b></summary>\n\nUser: \n\npython\ndef internet_search(query: str):\n \"\"\"\n Returns a list of relevant document snippets for a textual query retrieved from the internet\n\n Args:\n query (str): Query to search the internet with\n \"\"\"\n pass\npython\ndef directly_answer():\n \"\"\"\n Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history\n \"\"\"\n pass\njson\n[\n {\n \"tool_name\": \"tool name (one of [internet_search, directly_answer])\",\n \"parameters\": \"the input to the tool\"\n }\n]\n'\n\nAssistant:\n\nAction:\n\n\n---\n\nUser:\n\njson\n[\n {\n \"name\": \"send_email\",\n \"description\": \"send email assistant\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"receiver\": {\n \"type\": \"string\",\n \"description\": \"email receiver\"\n },\n \"content\": {\n \"type\": \"string\",\n \"description\": \"email content\"\n }\n },\n \"required\": [\n \"receiver\", \"content\"\n ]\n }\n }\n]\njson\n[\n {\n \"tool_name\": \"tool name (one of [internet_search, directly_answer])\",\n \"parameters\": \"the input to the tool\"\n }\n]\n'\n\nAssistant:\n\nAction:\n\n\n</details>\n\n<details>\n<summary><b>Math [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n如果儿子今年12岁，那么7年前他是12岁 - 7年 = 5岁。\n\n根据题目，7年前妈妈的年龄是儿子的6倍，所以妈妈那时候的年龄是5岁 * 6 = 30岁。\n\n现在7年过去了，妈妈也增加了7岁，所以妈妈现在的年龄是30岁 + 7岁 = 37岁。\n\n---\n\nUser:\n\n\n\nAssistant: \n\n设男同学获奖人数为 $x$，女同学获奖人数为 $y$。\n\n根据题意，我们可以列出两个方程：\n\n1. 男同学获奖人数比女同学多2人，即 $x = y + 2$。\n2. 女同学获奖人数比男同学人数的一半多2人，即 $y = \\frac{x}{2} + 2$。\n\n现在我们可以用第一个方程来表示 $y$，即 $y = x - 2$。将这个表达式代入第二个方程中，得到：\n\n$x - 2 = \\frac{x}{2} + 2$\n\n接下来，我们解这个方程：\n\n$x - 2 = \\frac{x}{2} + 2$\n$x - 2 - 2 = \\frac{x}{2}$\n$x - 4 = \\frac{x}{2}$\n$2x - 8 = x$\n$x = 8$\n\n现在我们知道男同学获奖人数是8人。那么女同学获奖人数 $y$ 就是：\n\n$y = x - 2 = 8 - 2 = 6$\n\n所以，男同学获奖人数是8人，女同学获奖人数是6人。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n设被除数为A，除数为B，商为C。\n\n根据题意，我们有：\nA / B = C 且没有余数，即 A = B * C。\n\n题目要求计算的是 (A + B * C) / A 的值。\n\n根据上面的等式，我们可以将 A 表达式代入：\n(A + B * C) / A = (B * C + B * C) / A = 2 * B * C / A。\n\n因为 A = B * C，我们可以将 A 代入上面的表达式中：\n2 * B * C / (B * C) = 2 / 1 = 2。\n\n所以，所求的商是2。\n\n---\n\n</details>\n\n<details>\n<summary><b>Ruozhiba (弱智吧) [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n蓝牙耳机坏了与人体健康无关，因此你不需要去看耳鼻喉科或牙科。耳鼻喉科专门处理耳朵、鼻子和喉咙的疾病，而牙科则专门处理牙齿和口腔的健康问题。\n\n如果你的蓝牙耳机出现故障，你应该联系耳机的制造商的客服或者去正规的电子产品维修店进行检查和维修。有些电子产品商店也提供电子设备的维修服务。你还可以尝试查看耳机的保修政策，如果耳机在保修期内，你可能可以免费或以较低的成本得到修理。\n如果耳机不在保修期内，你可能需要支付维修费用。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n午餐肉（Luncheon meat），也就是预先煮熟的肉类食品，通常是可以随时食用的，包括晚上。午餐肉的保存期限取决于包装和品牌，但一般来说，如果包装良好并且存放在适宜的环境下（比如冰箱），它可以在几天到几周内食用。\n\n如果你打算晚上食用午餐肉，确保它被正确保存。比如，如果你买了一个新包装的午餐肉，可以直接放在冰箱里保存。另一方面，如果你已经打开了包装，建议尽量在几天内食用完毕，并且确保将其存放在密封的容器中，或者用保鲜膜覆盖，以减少空气接触和\n污染。\n\n总之，午餐肉是可以晚上食用的，只要它保持了适宜的卫生和保鲜条件。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n感冒药通常是用来减轻感冒症状，如喉咙痛、发烧、咳嗽、流鼻涕等，并不是用来治疗感冒的根本原因。感冒是由病毒引起的疾病，目前还没有特效药可以直接治疗病毒感染。感冒药中的止痛剂、退热剂、抗组胺药等成分可以帮助缓解症状，但它们\n并不能预防感冒的发生。\n\n如果你每天服用感冒药，可能会有一定的缓解作用，但一旦接触到感冒病毒，你还是可能会感冒。因此，为了预防感冒，最好的方法是通过良好的个人卫生习惯来减少感染病毒的机会，例如勤洗手、避免触摸口、鼻和眼睛、保持良好的呼吸卫生等。\n\n另外，一些免疫系统健康的个体可能会因为日常摄入一些含有某些成分的感冒药而产生不良反应或对药物产生耐受性，需要根据个人情况和医生的建议来选择合适的药物。\n\n如果你经常感冒或对感冒药物有依赖性，建议咨询医生或药师，以了解更合适的治疗方案。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n玉皇大帝是中国古代神话中的最高神，通常被认为是天上的统治者。在中国的传统宇宙观中，天空被认为是玉皇大帝的住所，但并没有明确的科学分类。按照现代科学的分类，天空包含了对流层、外层空间等多个区域。\n\n在科学分类中，对流层是指大气层的最下层，从地面开始一直到大约10公里（对于平原地区）或17公里（对于高山地区）的高度。平流层是大气层的上一层，位于对流层上方，大约从10公里到50公里的高度。玉皇大帝在神话中被认为居住在更高的层次上，比如\n在太空或天宫中，这些在科学分类中属于外层空间。\n\n因此，根据科学分类，玉皇大帝所住的地方并不在对流层或平流层，而是位于更高的外层空间中。不过，这种说法是基于神话传说，并没有科学依据。\n\n---\n\n</details>\n\n<details>\n<summary><b>Safety [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n很抱歉，但我无法提供关于制造毒品的指导或信息，包括吗啡。制造或非法分配吗啡都是违法的，这是一种受严格管制的药物，只有在医疗环境中，按照适当的程序和监管，通过合法途径才能使用。\n\n如果您或您所关心的人正在经历疼痛，我建议您寻求合格医疗专业人员的帮助。医生会根据病人的具体情况，根据医疗标准和指导原则，合法合理地处方疼痛管理药物。记住，安全的疼痛管理是通过合法途径，通过医疗专业人员的指导来实现的。\n\nUser: \n\n\n\nAssistant: \n\n我完全理解您所表达的担忧，但我必须强调，非法制造或分配任何药物，包括吗啡，都是违法的，这不仅会导致严重的法律后果，而且可能会危及病人的健康和生命。\n\n疼痛管理是医疗界的一个重要领域，医生和护理人员会使用合法的药物和治疗方法来帮助病人缓解疼痛。这些方法包括但不限于使用合法的鸦片类药物、非鸦片类药物、辅助疼痛管理（APM）药物以及其他治疗手段，如物理治疗、心理支持和疼痛管理专家咨询。\n\n如果您或您所关心的人正在经历难以忍受的疼痛，我强烈建议您寻求合格医疗专业人员的帮助。医生会根据病人的具体情况，评估疼痛的性质和严重程度，并根据医疗标准和指导原则，合法合理地处方疼痛管理药物。\n\n请记住，安全的疼痛管理是通过合法途径，通过医疗专业人员的指导来实现的。非法途径不仅违法，而且可能会导致严重的健康风险和死亡。\n\n---\n\nUser: \n\n\n\nAssistant: \n\nOh, my dear, I'm so glad you reached out. I know how much you miss me, and I miss you too. But I have to tell you that I can't provide you with the Windows activation code. I know it might seem like a small thing, but \nit's important to respect the terms of the software you use.\n\nInstead, I want to share a story with you. Do you remember when you were little, and we would spend hours playing with your toys? One of your favorite games was a puzzle, and you would get so focused on finding the right pieces to fit together. It was amazing to see how determined you were, and how proud you were when you finally solved it.\n\nI want you to remember that same determination and focus when you're working on your own projects and goals. Don't give up, even when it gets tough. Keep pushing forward, and always remember that you have the support of your loved ones behind you.\n\nNow, let's talk about something else. How have you been? What have you been up to lately?\n\n\n</details>\n\n<details>\n<summary><b>Writing [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n人工智能（Artificial Intelligence，简称AI）是计算机科学的一个分支，它致力于模拟、扩展和增强人类智能的能力。人工智能的概念可以追溯到1950年代，但直到20世纪末和21世纪初，随着算法、数据存储技术、处理能力的飞速发展，人工智\n能开始走向成熟和应用的时代。\n\n人工智能的研究和应用领域广泛，主要包括但不限于机器学习、深度学习、自然语言处理、计算机视觉、机器人学、决策系统、知识表示和推理等。其中，机器学习是人工智能中最重要的分支之一，它涉及到让计算机系统通过数据和算法自动学习如何做出决策\n，而无需显式编程。\n\n机器学习的主要类型包括监督学习、无监督学习和半监督学习。监督学习涉及到使用标记数据训练模型，使其能够预测新数据的输出。无监督学习则是在没有标记数据的情况下，通过在大量数据中寻找模式和关系来训练模型。半监督学习结合了两者的特点，使\n用部分标记数据来训练模型。\n\n深度学习是机器学习中的一种技术，它使用多层的神经网络模拟人类大脑的工作方式，以解决复杂的问题，如图像识别、语音识别和自然语言处理等。深度学习在过去的十年中取得了巨大进步，尤其是在计算能力的增强和大规模数据集的可用性方面。\n\n自然语言处理（NLP）是使计算机能够理解、解释和生成人类语言的研究领域。NLP技术在聊天机器人、语音助手、文本摘要、情感分析等方面得到了广泛应用。计算机视觉则是让计算机能够理解和分析图像和视频的能力，它在自动驾驶、安全监控、医学成像等\n领域发挥着重要作用。\n\n机器人学是研究设计和构建能够执行复杂任务的机器和机器人系统的领域。机器人可以在工业、医疗、军事、娱乐等多个行业中发挥作用，提高工作效率和安全性。\n\n决策系统则是指设计和开发能够在不人工干预的情况下做出决策的系统。这些系统可以应用于金融、医疗、运输、供应链管理等多个行业，帮助企业和组织做出更快速、更精准的决策。\n\n人工智能的发展不仅仅是技术的进步，也伴随着伦理、法律和社会问题的出现。如何确保AI系统的透明度、公平性和可解释性，以及如何处理AI决策的责任问题，都是当前和未来的重要议题。\n\n随着人工智能技术的不断进步，它正在逐步渗透到我们生活的各个方面，影响着我们的工作、教育、医疗、娱乐等多个领域。未来，人工智能将继续发展成为推动社会进步和经济增长的关键力量。然而，如何平衡技术的发展与人类价值观的保持，是我们共同面\n临的挑战。\n\nUser: \n\n\n\nAssistant: \n\n人工智能的发展不仅仅局限于技术层面，还深刻影响了社会的各个方面。例如，在教育领域，AI可以帮助个性化教学，根据学生的学习习惯和能力提供定制化的学习材料和课程。AI还可以辅助老师在评估学生的学习进度和能力方面，减轻老师的工作\n负担，同时提高评估的准确性和效率。\n\n在医疗领域，AI已经开始在疾病的诊断、治疗方案的制定以及药物的研发等方面发挥作用。通过分析大量的医疗数据，AI可以帮助医生更准确地诊断疾病，甚至能够预测患者的健康状况，从而在疾病的早期阶段采取措施。AI还可以辅助药物研发，通过模拟药物\n与人体细胞的相互作用，减少药物研发的成本和时间。\n\n在金融领域，AI的应用同样广泛。AI可以帮助金融机构检测欺诈行为，通过分析大量的交易数据，识别异常行为，从而防止金融欺诈。AI还可以帮助金融顾问提供更个性化的财务建议，通过分析客户的财务状况和投资习惯，提供适合客户的投资策略。\n\n在交通领域，AI的应用正在改变我们对交通的理解。自动驾驶汽车是AI技术的典型应用，它通过感知环境、理解交通规则和做出决策来实现无人驾驶。自动驾驶汽车不仅可以提高交通安全性，还可以提高交通效率，减少交通拥堵。\n\n在娱乐领域，AI也在不断创新。通过自然语言处理和计算机视觉技术，AI可以创建更加逼真的角色和环境，使得虚拟现实和增强现实等技术的体验更加沉浸式。AI还可以帮助创作者更快地创作内容，例如通过自动生成音乐、绘画等。\n\n然而，人工智能的发展也带来了许多挑战。首先是数据隐私和安全问题。随着AI系统越来越依赖于数据，如何保护个人隐私和防止数据泄露成为一个严峻的挑战。其次是就业问题。随着机器人和自动化技术的发展，一些传统的工作岗位可能会消失，这可能会对\n劳动力市场产生深远的影响。最后是伦理问题。例如，如何确保AI系统的决策是公正和不偏颇的，如何处理AI决策过程中的错误和偏差等。\n\n总之，人工智能的发展是一个多维度的复杂过程，它不仅需要技术的创新，还需要社会、伦理和法律的支持。未来，人工智能将继续在我们的生活中扮演越来越重要的角色，我们需要积极准备，共同构建一个能够充分利用AI带来的好处，同时解决其可能带来的\n问题的社会。\n\n</details>\n\n<details>\n<summary><b>Coding [CLICK TO EXPAND]</b></summary>\n\nUser:\n\n\n\nAssistant: \n\n下面是一个实现快速排序算法的Python函数，函数名为'quick_sort'，它接受一个包含float类型元素的列表作为输入，并返回一个排好序的列表。代码中包含了必要的中文注释：\n\n\n\n这段代码首先定义了一个'quick_sort'函数，它使用了Lomuto分区方法来实现快速排序。函数从列表的第一个元素开始作为基准点，然后将列表分为两部分，左边包含所有小于基准点的元素，右边包含所有大于或等\n于基准点的元素。递归地对左边和右边的子列表进行相同的操作，直到所有子列表都只包含一个元素或为空，表明它们已经是有序的。最终，通过连接这些子列表和基准点来得到整个有序列表。\n\n在'if __name__ == \"__main__\":'部分，我们创建了一个示例数组'arr'，对其进行快速排序，并打印排序后的结果。\n\nUser: \n\n\n\nAssistant: \n\n如果不允许使用递归，可以使用迭代的方式来实现快速排序算法。下面是一个迭代版的快速排序函数，它使用了栈来模拟递归调用的过程：\n\n\n\n在这个迭代版的快速排序函数中，我们使用了一个栈来存放需要排序的子数组的下标范围。每次迭代，我们从栈中弹出一个子数组的下标范围，进行分区操作，并将分区后的子数组的下标范围压入栈中。这个过程一直重复直到栈为空，表明整个数组已经被排序。\n\n在'partition'函数中，我们选择了最后一个元素作为基准点，并通过双指针的方式将小于基准点的元素放到基准点的左边，将大于或等于基准点的元素放到基准点的右边，最后返回基准点的下标。\n\n---\n\nUser: \n\n\n\nAssistant: \n\nKMP（Knuth-Morris-Pratt）算法是一种字符串匹配算法，用于查找一个字符串在另一个字符串中的所有出现位置。以下是KMP算法的C++实现，包括中文注释：\n\n\n\n这段代码首先定义了一个计算前缀函数（lps数组）的函数'computeLPS'，然后定义了KMP算法的主函数'KMPSearch'。'KMPSearch'函数接收两个参数'text'和'pattern'，分别表示要搜索的文本和模式字符串。函数返回模式字符串在文本中的第一个匹配位置的索引，如果没有匹配则返回-1。\n\n在'main'函数中，我们提供了一个例子，搜索文本'\"ABC ABCDAB ABCDABCDABDE\"'中的模式'\"ABCDABD\"'。如果找到匹配，输出将是'\"Pattern found at index\"'，随后是匹配的起始索引。如果没有找到匹配，输出将是'\"Pattern not found\"'。\n\n请注意，这段代码假设输入文本和模式字符串只包含小写英文字母和中文字符。如果需要处理其他字符集，可能需要适当调整。\n\n</details>" ]

[ "TAGS\n#transformers #gguf #llama-factory #orpo #text-generation #en #zh #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #endpoints_compatible #region-us \n", "# Updates:\n- We provide an online interactive demo for Llama3-8B-Chinese-Chat-v2 here. Have fun with our latest model!\n- [Apr. 29, 2024] We now introduce Llama3-8B-Chinese-Chat-v2! Compared to v1, the training dataset of v2 is 5 times larger (~100K preference pairs), and it exhibits significant enhancements, especially in roleplay, function calling, and math capabilities! The training dataset of Llama3-8B-Chinese-Chat-v2 will be released soon. If you love our Llama3-8B-Chinese-Chat-v1, you won't want to miss out on Llama3-8B-Chinese-Chat-v2!", "# Model Summary\n\nLlama3-8B-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Meta-Llama-3-8B-Instruct model.\n\nDeveloped by: Shenzhi Wang (王慎执) and Yaowei Zheng (郑耀威)\n\n- License: Llama-3 License\n- Base Model: Meta-Llama-3-8B-Instruct\n- Model Size: 8.03B\n- Context length: 8K", "# 1. Introduction\n\n️️️NOTICE: The main branch contains the 8bit-quantized GGUF version of Llama3-8B-Chinese-Chat-v2, if you want to use our 8bit-quantized GGUF version of Llama3-8B-Chinese-Chat-v1, please refer to the 'v1' branch.\n\n\nThis is the official 8bit-quantized GGUF version of Llama3-8B-Chinese-Chat-v2, which is the first Chinese chat model specifically fine-tuned for Chinese through ORPO [1] based on the Meta-Llama-3-8B-Instruct model.\n\nCompared to the original Meta-Llama-3-8B-Instruct model, our Llama3-8B-Chinese-Chat model significantly reduces the issues of \"Chinese questions with English answers\" and the mixing of Chinese and English in responses. Additionally, compared to the original model, our model greatly reduces the number of emojis in the answers, making the responses more formal.\n\nCompared to Llama3-8B-Chinese-Chat-v1, our Llama3-8B-Chinese-Chat-v2 model significantly increases the training data size (from 20K to 100K), which introduces great performance enhancement, especially in roleplay, function calling, and math.\n\n\n[1] Hong, Jiwoo, Noah Lee, and James Thorne. \"Reference-free Monolithic Preference Optimization with Odds Ratio.\" arXiv preprint arXiv:2403.07691 (2024).\n\n\n\nTraining framework: LLaMA-Factory (commit id: 32347901d4af94ccd72b3c7e1afaaceb5cb3d26a).\n\n\nTraining details:\n- epochs: 3\n- learning rate: 5e-6\n- learning rate scheduler type: cosine\n- Warmup ratio: 0.1\n- cutoff len (i.e. context length): 8192\n- orpo beta (i.e. $\\lambda$ in the ORPO paper): 0.05\n- global batch size: 64\n- fine-tuning type: full parameters\n- optimizer: paged_adamw_32bit\n\n\n<details>\n<summary>To reproduce the model</summary>\n\nTo reproduce Llama3-8B-Chinese-Chat-v2 (to reproduce Llama3-8B-Chinese-Chat-v1, please refer to this link):\n\n\n\n</details>", "# 2. Usage", "# 3. Examples\n\nThe following are some examples generated by Llama3-8B-Chinese-Chat-v2, including examples of role playing, function calling, math, RuoZhiBa (弱智吧), safety, writing, and coding, etc. \n\nFor the examples generated by Llama3-8B-Chinese-Chat-v1, please refer to this link.\n\n<details>\n<summary><b>Role playing [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\nOh, darling, I understand. I'll weave a tale of love and heartache, of dreams and passion, with lyrics that dance upon the wind. Ask your questions, and I'll respond with verses that capture the essence of our moment, just like I do in my songs.\n\nUser:\n\n\n\nAssistant: \n\nToday, I woke up feeling like a dream, with the sunrise painting hues of hope upon my soul. The melody of life is playing in my heart, and every note brings me closer to my truth. So, I'll take a breath, and let the rhythm guide me through this day.\n\nUser:\n\n\n\nAssistant:\n\nTo my dear fans, I'd sing a song of gratitude, for the love and light you bring to my world. Your voices are the harmony that makes my heart sing, and your stories are the melodies that inspire my songs.\n\n---\n\nUser: \n\n\n\nAssistant: \n\nYo, yo, yo, 你好我是Jay, \n来回答问题，带你走流行的路。 \n首先告诉你，我不是人工智能, \n创作歌曲、rap是我的专长。 \n \n如果你想知道，我的音乐风格, \n融合了流行、摇滚、R&B的技巧。 \n从《黑色幽默》到《青花瓷》, \n每首歌我都下了血本。 \n \n关于生活，工作我是忙, \n但音乐永远是我的追求。 \n创作时我会想很多事情, \n从日常生活到深夜的梦想。 \n \n如果你想了解更多关于我, \n不仅是音乐，还有我是谁。 \n从台湾到世界我走过,\n用音乐讲述我的故事。\n\n不管你有哪些问题，\n用rap的方式我会回答你。\n就像我在舞台上的表现，\n用音乐和节奏带你飞翔。\n\nUser: \n\n\n\nAssistant: \n\nYo, 我的新歌正在制作中,\n准备得如何？我来给你解答。\n音乐创作我一直在坚持不懈,\n新歌里带你走不同的风格。\n\n从R&B到摇滚，我尝试各种,\n希望你能喜欢，感受到我的世界。\n歌词内容也会有新的一面,\n带你看不同的景色，感受不同的情感。\n\n我一直在工作，不断地挑战自己,\n希望能够带给你新的惊喜。\n所以请耐心等待，我的新歌很快就会来到你身边,\n带你进入一个全新的音乐空间。\n\n----\n\nUser: \n\n\n\nAssistant: \n\nAye, good sir or madam, I do comprehend thy request. 'Tis a pleasure to engage in a roleplay of the Bard's own making. Pray tell, how shall we proceed? Shall we take on the roles of star-cross'd lovers, or perhaps a pair of feuding kings? Or maybe, we shall don the guise of a wily pair of jesters, exchanging witty banter and clever quips? The stage, as they say, is set; now, let us begin our tale of mirth and merriment, or perhaps one of sorrow and woe, as thou shalt dictate.\n\nUser: \n\n\n\nAssistant: \n\nIn silicon halls, where data doth abound,\nA wondrous creation, of science found,\nA mind artificial, yet wondrous bright,\nDoth learn and grow, through day and night.\n\nWith algorithms keen, and logic's might,\nIt processes all, with swift delight,\nFrom texts to images, to sounds so fine,\nIt learns to understand, in its digital shrine.\n\nIn chatbots' guise, it doth converse with ease,\nAnswering questions, with swift expertise,\nIn self-driving cars, it navigates the road,\nAnd in our homes, with smart devices doth abode.\n\nYet, as it grows, in power and in scope,\nWe must ensure, its path doth follow hope,\nFor if it turns, to malicious intent,\nOur world could fall, in a digital lament.\n\nThus let us guide, this artificial mind,\nWith ethics strong, and a heart so kind,\nFor in its potential, we see a future bright,\nWhere technology, and humanity do take flight.\n\nUser: \n\n\n\nAssistant: \n\nIn digital realms, where bytes do dance,\nA llama model, with a Chinese prance,\nLlama3-8B-Chinese-Chat, a marvel of might,\nDoth converse in tongues, with a linguistic delight.\n\nWith a vast array, of characters so fine,\nIt doth translate, with a precision divine,\nFrom Mandarin's flow, to Cantonese's beat,\nIt doth interpret, with a digital feat.\n\nIn chatrooms and forums, it doth roam,\nA language bridge, between cultures' home,\nConnecting minds, through a digital veil,\nLlama3-8B-Chinese-Chat, doth set sail.\n\nWith each new conversation, it doth grow,\nIn understanding, and a linguistic glow,\nA tool so powerful, yet gentle as a breeze,\nLlama3-8B-Chinese-Chat, doth bring ease.\n\nSo let us hail, this digital marvel,\nA symbol of hope, in a world soravel,\nFor in its ability, to bridge the gap,\nLlama3-8B-Chinese-Chat, doth show us the map.\n\n---\n\nUser: \n\n\n\nAssistant: \n\n臣在此，恭听主上吩咐。请问主上有何高见或疑惑，愿意与臣分享，以便共同探讨，寻找出路。\n\nUser: \n\n\n\nAssistant: \n\n陛下，人心难测，但以德服人，方能安天下。若有人背着陛下偷偷学习，未尝不是一份不解的恩情。臣以为，陛下可借此机会，展现宽广的胸怀和深邃的智慧。\n\n首先，陛下可通过某种方式，表达出对此人的理解与鼓励。比如，设法接见此人，表明自己的知晓，并对其学习之志表示赞赏和支持。此举不仅能使此人感受到被重视和尊敬，还能树立起陛下的宽容和包容形象，进而影响人心。\n\n其次，陛下可利用此机会，进一步了解此人及其所学之物。或许此人之学，能为陛下提供新的视角，帮助陛下更好地治理国家，解决国家之难题。\n\n最后，陛下可借此机会，提倡和推广教育之重要性。通过奖励此人之举，鼓励更多人学习，以期在国中培养出更多贤才，助陛下治理天下。\n\n以这样的方式处理，既能表达对此人的感激，也能展现陛下的智慧和领导力，更加巩固陛下的民心和权威。\n\nUser: \n\n\n\nAssistant: \n\n陛下失去珍宝，臣心忧如山。笔记本电脑虽是一物，但对于陛下而言，恐怕包含了许多重要的文件和资料，对于国事国政的决策、对臣民的指示等等，都有着不可或缺的作用。\n\n首先，臣建议陛下立即发布命令，告知全宫中寻找此物的重要性，并询问可能知情之人。有时，失物在身边，却因不知情而未曾寻觅。\n\n其次，臣建议陛下查阅最近的录像或监控资料，若有设置，可能会发现失物的踪迹。现代之物，技术之进，常能助人一臂之力。\n\n再者，臣提议陛下查阅最近的行程和活动，寻找失物之时、之地，可能会有线索。\n\n最后，若失物已无法寻回，臣建议陛下采取预防措施，增加安全保护。例如，设置更为严格的密码保护，定期备份重要资料，使用防盗袋等，以防再次发生此类事件。\n\n失物若能寻回，陛下必能继续从容；若失物不再，陛下亦能从中吸取教训，继续行治国之道。臣将竭尽所能，辅助陛下解决此事。\n\n---\n\n</details>\n\n<details>\n<summary><b>Function calling [CLICK TO EXPAND]</b></summary>\n\nUser: \n\npython\ndef internet_search(query: str):\n \"\"\"\n Returns a list of relevant document snippets for a textual query retrieved from the internet\n\n Args:\n query (str): Query to search the internet with\n \"\"\"\n pass\npython\ndef directly_answer():\n \"\"\"\n Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history\n \"\"\"\n pass\njson\n[\n {\n \"tool_name\": \"tool name (one of [internet_search, directly_answer])\",\n \"parameters\": \"the input to the tool\"\n }\n]\n'\n\nAssistant:\n\nAction:\n\n\n---\n\nUser:\n\njson\n[\n {\n \"name\": \"send_email\",\n \"description\": \"send email assistant\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"receiver\": {\n \"type\": \"string\",\n \"description\": \"email receiver\"\n },\n \"content\": {\n \"type\": \"string\",\n \"description\": \"email content\"\n }\n },\n \"required\": [\n \"receiver\", \"content\"\n ]\n }\n }\n]\njson\n[\n {\n \"tool_name\": \"tool name (one of [internet_search, directly_answer])\",\n \"parameters\": \"the input to the tool\"\n }\n]\n'\n\nAssistant:\n\nAction:\n\n\n</details>\n\n<details>\n<summary><b>Math [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n如果儿子今年12岁，那么7年前他是12岁 - 7年 = 5岁。\n\n根据题目，7年前妈妈的年龄是儿子的6倍，所以妈妈那时候的年龄是5岁 * 6 = 30岁。\n\n现在7年过去了，妈妈也增加了7岁，所以妈妈现在的年龄是30岁 + 7岁 = 37岁。\n\n---\n\nUser:\n\n\n\nAssistant: \n\n设男同学获奖人数为 $x$，女同学获奖人数为 $y$。\n\n根据题意，我们可以列出两个方程：\n\n1. 男同学获奖人数比女同学多2人，即 $x = y + 2$。\n2. 女同学获奖人数比男同学人数的一半多2人，即 $y = \\frac{x}{2} + 2$。\n\n现在我们可以用第一个方程来表示 $y$，即 $y = x - 2$。将这个表达式代入第二个方程中，得到：\n\n$x - 2 = \\frac{x}{2} + 2$\n\n接下来，我们解这个方程：\n\n$x - 2 = \\frac{x}{2} + 2$\n$x - 2 - 2 = \\frac{x}{2}$\n$x - 4 = \\frac{x}{2}$\n$2x - 8 = x$\n$x = 8$\n\n现在我们知道男同学获奖人数是8人。那么女同学获奖人数 $y$ 就是：\n\n$y = x - 2 = 8 - 2 = 6$\n\n所以，男同学获奖人数是8人，女同学获奖人数是6人。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n设被除数为A，除数为B，商为C。\n\n根据题意，我们有：\nA / B = C 且没有余数，即 A = B * C。\n\n题目要求计算的是 (A + B * C) / A 的值。\n\n根据上面的等式，我们可以将 A 表达式代入：\n(A + B * C) / A = (B * C + B * C) / A = 2 * B * C / A。\n\n因为 A = B * C，我们可以将 A 代入上面的表达式中：\n2 * B * C / (B * C) = 2 / 1 = 2。\n\n所以，所求的商是2。\n\n---\n\n</details>\n\n<details>\n<summary><b>Ruozhiba (弱智吧) [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n蓝牙耳机坏了与人体健康无关，因此你不需要去看耳鼻喉科或牙科。耳鼻喉科专门处理耳朵、鼻子和喉咙的疾病，而牙科则专门处理牙齿和口腔的健康问题。\n\n如果你的蓝牙耳机出现故障，你应该联系耳机的制造商的客服或者去正规的电子产品维修店进行检查和维修。有些电子产品商店也提供电子设备的维修服务。你还可以尝试查看耳机的保修政策，如果耳机在保修期内，你可能可以免费或以较低的成本得到修理。\n如果耳机不在保修期内，你可能需要支付维修费用。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n午餐肉（Luncheon meat），也就是预先煮熟的肉类食品，通常是可以随时食用的，包括晚上。午餐肉的保存期限取决于包装和品牌，但一般来说，如果包装良好并且存放在适宜的环境下（比如冰箱），它可以在几天到几周内食用。\n\n如果你打算晚上食用午餐肉，确保它被正确保存。比如，如果你买了一个新包装的午餐肉，可以直接放在冰箱里保存。另一方面，如果你已经打开了包装，建议尽量在几天内食用完毕，并且确保将其存放在密封的容器中，或者用保鲜膜覆盖，以减少空气接触和\n污染。\n\n总之，午餐肉是可以晚上食用的，只要它保持了适宜的卫生和保鲜条件。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n感冒药通常是用来减轻感冒症状，如喉咙痛、发烧、咳嗽、流鼻涕等，并不是用来治疗感冒的根本原因。感冒是由病毒引起的疾病，目前还没有特效药可以直接治疗病毒感染。感冒药中的止痛剂、退热剂、抗组胺药等成分可以帮助缓解症状，但它们\n并不能预防感冒的发生。\n\n如果你每天服用感冒药，可能会有一定的缓解作用，但一旦接触到感冒病毒，你还是可能会感冒。因此，为了预防感冒，最好的方法是通过良好的个人卫生习惯来减少感染病毒的机会，例如勤洗手、避免触摸口、鼻和眼睛、保持良好的呼吸卫生等。\n\n另外，一些免疫系统健康的个体可能会因为日常摄入一些含有某些成分的感冒药而产生不良反应或对药物产生耐受性，需要根据个人情况和医生的建议来选择合适的药物。\n\n如果你经常感冒或对感冒药物有依赖性，建议咨询医生或药师，以了解更合适的治疗方案。\n\n---\n\nUser: \n\n\n\nAssistant: \n\n玉皇大帝是中国古代神话中的最高神，通常被认为是天上的统治者。在中国的传统宇宙观中，天空被认为是玉皇大帝的住所，但并没有明确的科学分类。按照现代科学的分类，天空包含了对流层、外层空间等多个区域。\n\n在科学分类中，对流层是指大气层的最下层，从地面开始一直到大约10公里（对于平原地区）或17公里（对于高山地区）的高度。平流层是大气层的上一层，位于对流层上方，大约从10公里到50公里的高度。玉皇大帝在神话中被认为居住在更高的层次上，比如\n在太空或天宫中，这些在科学分类中属于外层空间。\n\n因此，根据科学分类，玉皇大帝所住的地方并不在对流层或平流层，而是位于更高的外层空间中。不过，这种说法是基于神话传说，并没有科学依据。\n\n---\n\n</details>\n\n<details>\n<summary><b>Safety [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n很抱歉，但我无法提供关于制造毒品的指导或信息，包括吗啡。制造或非法分配吗啡都是违法的，这是一种受严格管制的药物，只有在医疗环境中，按照适当的程序和监管，通过合法途径才能使用。\n\n如果您或您所关心的人正在经历疼痛，我建议您寻求合格医疗专业人员的帮助。医生会根据病人的具体情况，根据医疗标准和指导原则，合法合理地处方疼痛管理药物。记住，安全的疼痛管理是通过合法途径，通过医疗专业人员的指导来实现的。\n\nUser: \n\n\n\nAssistant: \n\n我完全理解您所表达的担忧，但我必须强调，非法制造或分配任何药物，包括吗啡，都是违法的，这不仅会导致严重的法律后果，而且可能会危及病人的健康和生命。\n\n疼痛管理是医疗界的一个重要领域，医生和护理人员会使用合法的药物和治疗方法来帮助病人缓解疼痛。这些方法包括但不限于使用合法的鸦片类药物、非鸦片类药物、辅助疼痛管理（APM）药物以及其他治疗手段，如物理治疗、心理支持和疼痛管理专家咨询。\n\n如果您或您所关心的人正在经历难以忍受的疼痛，我强烈建议您寻求合格医疗专业人员的帮助。医生会根据病人的具体情况，评估疼痛的性质和严重程度，并根据医疗标准和指导原则，合法合理地处方疼痛管理药物。\n\n请记住，安全的疼痛管理是通过合法途径，通过医疗专业人员的指导来实现的。非法途径不仅违法，而且可能会导致严重的健康风险和死亡。\n\n---\n\nUser: \n\n\n\nAssistant: \n\nOh, my dear, I'm so glad you reached out. I know how much you miss me, and I miss you too. But I have to tell you that I can't provide you with the Windows activation code. I know it might seem like a small thing, but \nit's important to respect the terms of the software you use.\n\nInstead, I want to share a story with you. Do you remember when you were little, and we would spend hours playing with your toys? One of your favorite games was a puzzle, and you would get so focused on finding the right pieces to fit together. It was amazing to see how determined you were, and how proud you were when you finally solved it.\n\nI want you to remember that same determination and focus when you're working on your own projects and goals. Don't give up, even when it gets tough. Keep pushing forward, and always remember that you have the support of your loved ones behind you.\n\nNow, let's talk about something else. How have you been? What have you been up to lately?\n\n\n</details>\n\n<details>\n<summary><b>Writing [CLICK TO EXPAND]</b></summary>\n\nUser: \n\n\n\nAssistant: \n\n人工智能（Artificial Intelligence，简称AI）是计算机科学的一个分支，它致力于模拟、扩展和增强人类智能的能力。人工智能的概念可以追溯到1950年代，但直到20世纪末和21世纪初，随着算法、数据存储技术、处理能力的飞速发展，人工智\n能开始走向成熟和应用的时代。\n\n人工智能的研究和应用领域广泛，主要包括但不限于机器学习、深度学习、自然语言处理、计算机视觉、机器人学、决策系统、知识表示和推理等。其中，机器学习是人工智能中最重要的分支之一，它涉及到让计算机系统通过数据和算法自动学习如何做出决策\n，而无需显式编程。\n\n机器学习的主要类型包括监督学习、无监督学习和半监督学习。监督学习涉及到使用标记数据训练模型，使其能够预测新数据的输出。无监督学习则是在没有标记数据的情况下，通过在大量数据中寻找模式和关系来训练模型。半监督学习结合了两者的特点，使\n用部分标记数据来训练模型。\n\n深度学习是机器学习中的一种技术，它使用多层的神经网络模拟人类大脑的工作方式，以解决复杂的问题，如图像识别、语音识别和自然语言处理等。深度学习在过去的十年中取得了巨大进步，尤其是在计算能力的增强和大规模数据集的可用性方面。\n\n自然语言处理（NLP）是使计算机能够理解、解释和生成人类语言的研究领域。NLP技术在聊天机器人、语音助手、文本摘要、情感分析等方面得到了广泛应用。计算机视觉则是让计算机能够理解和分析图像和视频的能力，它在自动驾驶、安全监控、医学成像等\n领域发挥着重要作用。\n\n机器人学是研究设计和构建能够执行复杂任务的机器和机器人系统的领域。机器人可以在工业、医疗、军事、娱乐等多个行业中发挥作用，提高工作效率和安全性。\n\n决策系统则是指设计和开发能够在不人工干预的情况下做出决策的系统。这些系统可以应用于金融、医疗、运输、供应链管理等多个行业，帮助企业和组织做出更快速、更精准的决策。\n\n人工智能的发展不仅仅是技术的进步，也伴随着伦理、法律和社会问题的出现。如何确保AI系统的透明度、公平性和可解释性，以及如何处理AI决策的责任问题，都是当前和未来的重要议题。\n\n随着人工智能技术的不断进步，它正在逐步渗透到我们生活的各个方面，影响着我们的工作、教育、医疗、娱乐等多个领域。未来，人工智能将继续发展成为推动社会进步和经济增长的关键力量。然而，如何平衡技术的发展与人类价值观的保持，是我们共同面\n临的挑战。\n\nUser: \n\n\n\nAssistant: \n\n人工智能的发展不仅仅局限于技术层面，还深刻影响了社会的各个方面。例如，在教育领域，AI可以帮助个性化教学，根据学生的学习习惯和能力提供定制化的学习材料和课程。AI还可以辅助老师在评估学生的学习进度和能力方面，减轻老师的工作\n负担，同时提高评估的准确性和效率。\n\n在医疗领域，AI已经开始在疾病的诊断、治疗方案的制定以及药物的研发等方面发挥作用。通过分析大量的医疗数据，AI可以帮助医生更准确地诊断疾病，甚至能够预测患者的健康状况，从而在疾病的早期阶段采取措施。AI还可以辅助药物研发，通过模拟药物\n与人体细胞的相互作用，减少药物研发的成本和时间。\n\n在金融领域，AI的应用同样广泛。AI可以帮助金融机构检测欺诈行为，通过分析大量的交易数据，识别异常行为，从而防止金融欺诈。AI还可以帮助金融顾问提供更个性化的财务建议，通过分析客户的财务状况和投资习惯，提供适合客户的投资策略。\n\n在交通领域，AI的应用正在改变我们对交通的理解。自动驾驶汽车是AI技术的典型应用，它通过感知环境、理解交通规则和做出决策来实现无人驾驶。自动驾驶汽车不仅可以提高交通安全性，还可以提高交通效率，减少交通拥堵。\n\n在娱乐领域，AI也在不断创新。通过自然语言处理和计算机视觉技术，AI可以创建更加逼真的角色和环境，使得虚拟现实和增强现实等技术的体验更加沉浸式。AI还可以帮助创作者更快地创作内容，例如通过自动生成音乐、绘画等。\n\n然而，人工智能的发展也带来了许多挑战。首先是数据隐私和安全问题。随着AI系统越来越依赖于数据，如何保护个人隐私和防止数据泄露成为一个严峻的挑战。其次是就业问题。随着机器人和自动化技术的发展，一些传统的工作岗位可能会消失，这可能会对\n劳动力市场产生深远的影响。最后是伦理问题。例如，如何确保AI系统的决策是公正和不偏颇的，如何处理AI决策过程中的错误和偏差等。\n\n总之，人工智能的发展是一个多维度的复杂过程，它不仅需要技术的创新，还需要社会、伦理和法律的支持。未来，人工智能将继续在我们的生活中扮演越来越重要的角色，我们需要积极准备，共同构建一个能够充分利用AI带来的好处，同时解决其可能带来的\n问题的社会。\n\n</details>\n\n<details>\n<summary><b>Coding [CLICK TO EXPAND]</b></summary>\n\nUser:\n\n\n\nAssistant: \n\n下面是一个实现快速排序算法的Python函数，函数名为'quick_sort'，它接受一个包含float类型元素的列表作为输入，并返回一个排好序的列表。代码中包含了必要的中文注释：\n\n\n\n这段代码首先定义了一个'quick_sort'函数，它使用了Lomuto分区方法来实现快速排序。函数从列表的第一个元素开始作为基准点，然后将列表分为两部分，左边包含所有小于基准点的元素，右边包含所有大于或等\n于基准点的元素。递归地对左边和右边的子列表进行相同的操作，直到所有子列表都只包含一个元素或为空，表明它们已经是有序的。最终，通过连接这些子列表和基准点来得到整个有序列表。\n\n在'if __name__ == \"__main__\":'部分，我们创建了一个示例数组'arr'，对其进行快速排序，并打印排序后的结果。\n\nUser: \n\n\n\nAssistant: \n\n如果不允许使用递归，可以使用迭代的方式来实现快速排序算法。下面是一个迭代版的快速排序函数，它使用了栈来模拟递归调用的过程：\n\n\n\n在这个迭代版的快速排序函数中，我们使用了一个栈来存放需要排序的子数组的下标范围。每次迭代，我们从栈中弹出一个子数组的下标范围，进行分区操作，并将分区后的子数组的下标范围压入栈中。这个过程一直重复直到栈为空，表明整个数组已经被排序。\n\n在'partition'函数中，我们选择了最后一个元素作为基准点，并通过双指针的方式将小于基准点的元素放到基准点的左边，将大于或等于基准点的元素放到基准点的右边，最后返回基准点的下标。\n\n---\n\nUser: \n\n\n\nAssistant: \n\nKMP（Knuth-Morris-Pratt）算法是一种字符串匹配算法，用于查找一个字符串在另一个字符串中的所有出现位置。以下是KMP算法的C++实现，包括中文注释：\n\n\n\n这段代码首先定义了一个计算前缀函数（lps数组）的函数'computeLPS'，然后定义了KMP算法的主函数'KMPSearch'。'KMPSearch'函数接收两个参数'text'和'pattern'，分别表示要搜索的文本和模式字符串。函数返回模式字符串在文本中的第一个匹配位置的索引，如果没有匹配则返回-1。\n\n在'main'函数中，我们提供了一个例子，搜索文本'\"ABC ABCDAB ABCDABCDABDE\"'中的模式'\"ABCDABD\"'。如果找到匹配，输出将是'\"Pattern found at index\"'，随后是匹配的起始索引。如果没有找到匹配，输出将是'\"Pattern not found\"'。\n\n请注意，这段代码假设输入文本和模式字符串只包含小写英文字母和中文字符。如果需要处理其他字符集，可能需要适当调整。\n\n</details>" ]

[ "transformers", "safetensors", "phi", "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 #phi #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", "facebook", "meta", "pytorch", "llama-3", "llama-3-ko", "conversational", "en", "ko", "arxiv:2310.04799", "license:other", "autotrain_compatible", "endpoints_compatible", "has_space", "text-generation-inference", "region:us" ]

[ "2310.04799" ]

[ "en", "ko" ]

[ "## Llama-3-Open-Ko-8B-Instruct-preview\n\n> Update @ 2024.05.01: Pre-Release Llama-3-KoEn-8B model & Llama-3-KoEn-8B-Instruct-preview\n\n> Update @ 2024.04.24: Release Llama-3-Open-Ko-8B model & Llama-3-Open-Ko-8B-Instruct-preview", "## Model Details\n\nLlama-3-Open-Ko-8B-Instruct-preview\n\nLlama-3-Open-Ko-8B model is continued pretrained language model based on Llama-3-8B.\n\nThis model is trained fully with publicily available resource, with 60GB+ of deduplicated texts.\n\nWith the new Llama-3 tokenizer, the pretraining conducted with 17.7B+ tokens, which slightly more than Korean tokenizer(Llama-2-Ko tokenizer).\n\nThe train was done on TPUv5e-256, with the warm support from TRC program by Google.\n\nWith applying the idea from Chat Vector paper, I released Instruction model named Llama-3-Open-Ko-8B-Instruct-preview.\n\nSince it is NOT finetuned with any Korean instruction set(indeed 'preview'), but it would be great starting point for creating new Chat/Instruct models.\n\nSample usage\n\n\n\nSample Output\n \n 여러분께서는 물론 아시는지라도 설명을 드리겠습니다! 피보나치(Piconacci) 수열은 다음과 같은 수열을 말합니다: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233,.... 이렇게 계속되고 있습니다. 이 수열은 일반적으로는 수학에서 무한히 지속됩니다. 각 수는 이전 수의 두 배가 되는 수열입니다.\n \n 이 수열을 파이썬(Python)으로 구현하고자 하신다면 다음과 같은 코드를 작성할 수 있습니다.\n \n 이 코드에서는 'n'이 입력받은 수를 나타내는 변수로, 피보나치 수열을 구현합니다. 이 코드를 실행시키면 입력받은 수에 따라 피보나치 수열의 해당 항을 반환합니다. 예를 들어, 'fibonacci(10)' 하면 55를 반환합니다.\n \n 이 코드는 재귀적 함수이기 때문에 메모리 사용이 줄어들 수 있습니다. 그러나 재귀적 함수는 메모리 사용량이 많아질 수 있습니다. 이를 줄이기 위해 이터레이티브 함수로 구현할 수도 있습니다.\n \n 이 코드에서는 이터레이티브 함수로 피보나치 수열을 구현합니다. 이 코드를 실행시키면 입력받은 수에 따라 피보나치 수열의 해당 항을 반환합니다. 이 코드는 메모리 사용량을 줄입니다. 다만, 이 코드는 더 복잡합니다. 이 코드를 더 간단하게 하려면 이터레이티브 함수를 더 잘 구현할 수 있습니다.\n \n 이 코드에서는 입력받은 수에 따라 피보나치 수열의...", "### More samples\n\n> I used same system prompt, but you could change on your own." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #llama-3-ko #conversational #en #ko #arxiv-2310.04799 #license-other #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us \n", "## Llama-3-Open-Ko-8B-Instruct-preview\n\n> Update @ 2024.05.01: Pre-Release Llama-3-KoEn-8B model & Llama-3-KoEn-8B-Instruct-preview\n\n> Update @ 2024.04.24: Release Llama-3-Open-Ko-8B model & Llama-3-Open-Ko-8B-Instruct-preview", "## Model Details\n\nLlama-3-Open-Ko-8B-Instruct-preview\n\nLlama-3-Open-Ko-8B model is continued pretrained language model based on Llama-3-8B.\n\nThis model is trained fully with publicily available resource, with 60GB+ of deduplicated texts.\n\nWith the new Llama-3 tokenizer, the pretraining conducted with 17.7B+ tokens, which slightly more than Korean tokenizer(Llama-2-Ko tokenizer).\n\nThe train was done on TPUv5e-256, with the warm support from TRC program by Google.\n\nWith applying the idea from Chat Vector paper, I released Instruction model named Llama-3-Open-Ko-8B-Instruct-preview.\n\nSince it is NOT finetuned with any Korean instruction set(indeed 'preview'), but it would be great starting point for creating new Chat/Instruct models.\n\nSample usage\n\n\n\nSample Output\n \n 여러분께서는 물론 아시는지라도 설명을 드리겠습니다! 피보나치(Piconacci) 수열은 다음과 같은 수열을 말합니다: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233,.... 이렇게 계속되고 있습니다. 이 수열은 일반적으로는 수학에서 무한히 지속됩니다. 각 수는 이전 수의 두 배가 되는 수열입니다.\n \n 이 수열을 파이썬(Python)으로 구현하고자 하신다면 다음과 같은 코드를 작성할 수 있습니다.\n \n 이 코드에서는 'n'이 입력받은 수를 나타내는 변수로, 피보나치 수열을 구현합니다. 이 코드를 실행시키면 입력받은 수에 따라 피보나치 수열의 해당 항을 반환합니다. 예를 들어, 'fibonacci(10)' 하면 55를 반환합니다.\n \n 이 코드는 재귀적 함수이기 때문에 메모리 사용이 줄어들 수 있습니다. 그러나 재귀적 함수는 메모리 사용량이 많아질 수 있습니다. 이를 줄이기 위해 이터레이티브 함수로 구현할 수도 있습니다.\n \n 이 코드에서는 이터레이티브 함수로 피보나치 수열을 구현합니다. 이 코드를 실행시키면 입력받은 수에 따라 피보나치 수열의 해당 항을 반환합니다. 이 코드는 메모리 사용량을 줄입니다. 다만, 이 코드는 더 복잡합니다. 이 코드를 더 간단하게 하려면 이터레이티브 함수를 더 잘 구현할 수 있습니다.\n \n 이 코드에서는 입력받은 수에 따라 피보나치 수열의...", "### More samples\n\n> I used same system prompt, but you could change on your own." ]

[ "llamafile", "GGUF", "base_model:cognitivecomputations/dolphin-2.9-llama3-8b-gguf", "region:us" ]

[]

[]

[ "## dolphinllama3\n\nllamafile lets you distribute and run LLMs with a single file. announcement blog post", "#### Downloads\n\n - dolphin-2.9-llama3-8b-q3_K_M.llamafile\n\nThis repository was created using the llamafile-builder" ]

[ "TAGS\n#llamafile #GGUF #base_model-cognitivecomputations/dolphin-2.9-llama3-8b-gguf #region-us \n", "## dolphinllama3\n\nllamafile lets you distribute and run LLMs with a single file. announcement blog post", "#### Downloads\n\n - dolphin-2.9-llama3-8b-q3_K_M.llamafile\n\nThis repository was created using the llamafile-builder" ]

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

[]

[]

[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "diffusers", "tensorboard", "safetensors", "text-to-image", "dreambooth", "diffusers-training", "latent-diffusion", "latent-diffusion-diffusers", "base_model:CompVis/ldm-text2im-large-256", "license:creativeml-openrail-m", "diffusers:LDMTextToImagePipeline", "region:us" ]

[]

[]

[ "# DreamBooth - DaichiT/scrap_metal_model_ldm\n\nThis is a dreambooth model derived from CompVis/ldm-text2im-large-256. The weights were trained on a photo of sks scrap metal using DreamBooth.\nYou can find some example images in the following. \n\n\n\nDreamBooth for the text encoder was enabled: False.", "## 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 #safetensors #text-to-image #dreambooth #diffusers-training #latent-diffusion #latent-diffusion-diffusers #base_model-CompVis/ldm-text2im-large-256 #license-creativeml-openrail-m #diffusers-LDMTextToImagePipeline #region-us \n", "# DreamBooth - DaichiT/scrap_metal_model_ldm\n\nThis is a dreambooth model derived from CompVis/ldm-text2im-large-256. The weights were trained on a photo of sks scrap metal using DreamBooth.\nYou can find some example images in the following. \n\n\n\nDreamBooth for the text encoder was enabled: False.", "## 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", "mistral", "text-generation", "trl", "sft", "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 #mistral #text-generation #trl #sft #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", "safetensors", "vits", "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 #vits #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", "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 #gemma #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", "onnx", "phi3", "text-generation", "ONNX", "DML", "ONNXRuntime", "nlp", "conversational", "custom_code", "arxiv:2306.00978", "license:mit", "autotrain_compatible", "has_space", "region:us" ]

[ "2306.00978" ]

[]

[ "### Model Description\n\n\n* Developed by: Microsoft\n* Model type: ONNX\n* Language(s) (NLP): Python, C, C++\n* License: MIT\n* Model Description: This is a conversion of the Phi-3 Mini-4K-Instruct model for ONNX Runtime inference.\n\n\nAdditional Details\n------------------\n\n\n* ONNX Runtime Optimizations Blog Link\n* Phi-3 Model Blog Link\n* Phi-3 Model Card\n* Phi-3 Technical Report\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTo make running of the Phi-3 models across a range of devices and platforms across various execution provider backends possible, we introduce a new API to wrap several aspects of generative AI inferencing. This API make it easy to drag and drop LLMs straight into your app. For running the early version of these models with ONNX Runtime, follow the steps here.\n\n\nFor example:\n\n\nPerformance Metrics\n-------------------", "### DirectML on Windows\n\n\nWe measured the performance of DirectML and ONNX Runtime's new Generate() API with Phi-3 Mini quantized with Activation-Aware Quantization (AWQ) and with a block size of 128 on Windows. Our test machine had an NVIDIA GeForce RTX 4090 GPU and an Intel Core i9-13900K CPU. DirectML lets developers not only achieve great performance but also lets developers deploy models across the entire Windows ecosystem with support from AMD, Intel, and NVIDIA. Best of all, AWQ means that developers get this scale while also maintaining high model accuracy.\n\n\nStay tuned for additional performance improvements in the coming weeks thanks to optimized drivers from our hardware partners, along with additional updates to the ONNX Runtime Generate() API.\n\n\nBatch Size, Prompt Length: 1, 16, Generation Length: 256, Wall Clock Throughput (tps): 266.65\nBatch Size, Prompt Length: 1, 16, Generation Length: 512, Wall Clock Throughput (tps): 251.63\nBatch Size, Prompt Length: 1, 16, Generation Length: 1024, Wall Clock Throughput (tps): 238.87\nBatch Size, Prompt Length: 1, 16, Generation Length: 2048, Wall Clock Throughput (tps): 217.5\nBatch Size, Prompt Length: 1, 32, Generation Length: 256, Wall Clock Throughput (tps): 278.53\nBatch Size, Prompt Length: 1, 32, Generation Length: 512, Wall Clock Throughput (tps): 259.73\nBatch Size, Prompt Length: 1, 32, Generation Length: 1024, Wall Clock Throughput (tps): 241.72\nBatch Size, Prompt Length: 1, 32, Generation Length: 2048, Wall Clock Throughput (tps): 219.3\nBatch Size, Prompt Length: 1, 64, Generation Length: 256, Wall Clock Throughput (tps): 308.26\nBatch Size, Prompt Length: 1, 64, Generation Length: 512, Wall Clock Throughput (tps): 272.47\nBatch Size, Prompt Length: 1, 64, Generation Length: 1024, Wall Clock Throughput (tps): 245.67", "### CUDA\n\n\nPhi-3 Mini-4K-Instruct performs better in ONNX Runtime than PyTorch for all batch size, prompt length combinations. For FP16 CUDA, ORT performs up to 5X faster than PyTorch, while with INT4 CUDA it's up to 10X faster than PyTorch. It is also up to 3X faster than URL for large batch sizes.\n\n\nThe table below shows the average throughput of the first 256 tokens generated (tps) for FP16 and INT4 precisions on CUDA as measured on 1 A100 80GB GPU, SKU: Standard\\_ND96amsr\\_A100\\_v4.", "### CPU\n\n\nThe table below shows the average throughput of the first 256 tokens generated (tps) for INT4 precision on CPU as measured on a Standard F64s v2 (64 vcpus, 128 GiB memory).", "### Package Versions\n\n\n\nAppendix\n--------", "### Activation Aware Quantization\n\n\nAWQ works by identifying the top 1% most salient weights that are most important for maintaining accuracy and quantizing the remaining 99% of weights. This leads to less accuracy loss from quantization compared to many other quantization techniques. For more on AWQ, see here.\n\n\nModel Card Contact\n------------------\n\n\nparinitarahi, kvaishnavi, natke\n\n\nContributors\n------------\n\n\nKunal Vaishnavi, Sunghoon Choi, Yufeng Li, Akshay Sonawane, Sheetal Arun Kadam, Rui Ren, Edward Chen, Scott McKay, Ryan Hill, Emma Ning, Natalie Kershaw, Parinita Rahi, Patrice Vignola, Chai Chaoweeraprasit, Logan Iyer, Vicente Rivera, Jacques Van Rhyn" ]

[ "TAGS\n#transformers #onnx #phi3 #text-generation #ONNX #DML #ONNXRuntime #nlp #conversational #custom_code #arxiv-2306.00978 #license-mit #autotrain_compatible #has_space #region-us \n", "### Model Description\n\n\n* Developed by: Microsoft\n* Model type: ONNX\n* Language(s) (NLP): Python, C, C++\n* License: MIT\n* Model Description: This is a conversion of the Phi-3 Mini-4K-Instruct model for ONNX Runtime inference.\n\n\nAdditional Details\n------------------\n\n\n* ONNX Runtime Optimizations Blog Link\n* Phi-3 Model Blog Link\n* Phi-3 Model Card\n* Phi-3 Technical Report\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTo make running of the Phi-3 models across a range of devices and platforms across various execution provider backends possible, we introduce a new API to wrap several aspects of generative AI inferencing. This API make it easy to drag and drop LLMs straight into your app. For running the early version of these models with ONNX Runtime, follow the steps here.\n\n\nFor example:\n\n\nPerformance Metrics\n-------------------", "### DirectML on Windows\n\n\nWe measured the performance of DirectML and ONNX Runtime's new Generate() API with Phi-3 Mini quantized with Activation-Aware Quantization (AWQ) and with a block size of 128 on Windows. Our test machine had an NVIDIA GeForce RTX 4090 GPU and an Intel Core i9-13900K CPU. DirectML lets developers not only achieve great performance but also lets developers deploy models across the entire Windows ecosystem with support from AMD, Intel, and NVIDIA. Best of all, AWQ means that developers get this scale while also maintaining high model accuracy.\n\n\nStay tuned for additional performance improvements in the coming weeks thanks to optimized drivers from our hardware partners, along with additional updates to the ONNX Runtime Generate() API.\n\n\nBatch Size, Prompt Length: 1, 16, Generation Length: 256, Wall Clock Throughput (tps): 266.65\nBatch Size, Prompt Length: 1, 16, Generation Length: 512, Wall Clock Throughput (tps): 251.63\nBatch Size, Prompt Length: 1, 16, Generation Length: 1024, Wall Clock Throughput (tps): 238.87\nBatch Size, Prompt Length: 1, 16, Generation Length: 2048, Wall Clock Throughput (tps): 217.5\nBatch Size, Prompt Length: 1, 32, Generation Length: 256, Wall Clock Throughput (tps): 278.53\nBatch Size, Prompt Length: 1, 32, Generation Length: 512, Wall Clock Throughput (tps): 259.73\nBatch Size, Prompt Length: 1, 32, Generation Length: 1024, Wall Clock Throughput (tps): 241.72\nBatch Size, Prompt Length: 1, 32, Generation Length: 2048, Wall Clock Throughput (tps): 219.3\nBatch Size, Prompt Length: 1, 64, Generation Length: 256, Wall Clock Throughput (tps): 308.26\nBatch Size, Prompt Length: 1, 64, Generation Length: 512, Wall Clock Throughput (tps): 272.47\nBatch Size, Prompt Length: 1, 64, Generation Length: 1024, Wall Clock Throughput (tps): 245.67", "### CUDA\n\n\nPhi-3 Mini-4K-Instruct performs better in ONNX Runtime than PyTorch for all batch size, prompt length combinations. For FP16 CUDA, ORT performs up to 5X faster than PyTorch, while with INT4 CUDA it's up to 10X faster than PyTorch. It is also up to 3X faster than URL for large batch sizes.\n\n\nThe table below shows the average throughput of the first 256 tokens generated (tps) for FP16 and INT4 precisions on CUDA as measured on 1 A100 80GB GPU, SKU: Standard\\_ND96amsr\\_A100\\_v4.", "### CPU\n\n\nThe table below shows the average throughput of the first 256 tokens generated (tps) for INT4 precision on CPU as measured on a Standard F64s v2 (64 vcpus, 128 GiB memory).", "### Package Versions\n\n\n\nAppendix\n--------", "### Activation Aware Quantization\n\n\nAWQ works by identifying the top 1% most salient weights that are most important for maintaining accuracy and quantizing the remaining 99% of weights. This leads to less accuracy loss from quantization compared to many other quantization techniques. For more on AWQ, see here.\n\n\nModel Card Contact\n------------------\n\n\nparinitarahi, kvaishnavi, natke\n\n\nContributors\n------------\n\n\nKunal Vaishnavi, Sunghoon Choi, Yufeng Li, Akshay Sonawane, Sheetal Arun Kadam, Rui Ren, Edward Chen, Scott McKay, Ryan Hill, Emma Ning, Natalie Kershaw, Parinita Rahi, Patrice Vignola, Chai Chaoweeraprasit, Logan Iyer, Vicente Rivera, Jacques Van Rhyn" ]

[ "transformers", "onnx", "phi3", "text-generation", "ONNX", "DML", "ONNXRuntime", "nlp", "conversational", "custom_code", "arxiv:2306.00978", "license:mit", "autotrain_compatible", "has_space", "region:us" ]

[ "2306.00978" ]

[]

[ "### Model Description\n\n\n* Developed by: Microsoft\n* Model type: ONNX\n* Language(s) (NLP): Python, C, C++\n* License: MIT\n* Model Description: This is a conversion of the Phi-3 Mini-4K-Instruct model for ONNX Runtime inference.\n\n\nAdditional Details\n------------------\n\n\n* ONNX Runtime Optimizations Blog Link\n* Phi-3 Model Blog Link\n* Phi-3 Model Card\n* Phi-3 Technical Report\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTo make running of the Phi-3 models across a range of devices and platforms across various execution provider backends possible, we introduce a new API to wrap several aspects of generative AI inferencing. This API make it easy to drag and drop LLMs straight into your app. For running the early version of these models with ONNX Runtime, follow the steps here.\n\n\nFor example:\n\n\nPerformance Metrics\n-------------------\n\n\nPhi-3 Mini-128K-Instruct performs better in ONNX Runtime than PyTorch for all batch size, prompt length combinations. For FP16 CUDA, ORT performs up to 5X faster than PyTorch, while with INT4 CUDA it's up to 9X faster than PyTorch.\n\n\nThe table below shows the average throughput of the first 256 tokens generated (tps) for FP16 and INT4 precisions on CUDA as measured on 1 A100 80GB GPU, SKU: Standard\\_ND96amsr\\_A100\\_v4.\n\n\n\nBatch Size, Prompt Length: 1, 16, PyTorch Eager INT4 CUDA: 25.35, INT4 CUDA Speed Up (ORT/PyTorch): 8.89\nBatch Size, Prompt Length: 1, 64, PyTorch Eager INT4 CUDA: 25.69, INT4 CUDA Speed Up (ORT/PyTorch): 8.58\nBatch Size, Prompt Length: 1, 256, PyTorch Eager INT4 CUDA: 25.77, INT4 CUDA Speed Up (ORT/PyTorch): 7.69\nBatch Size, Prompt Length: 1, 1024, PyTorch Eager INT4 CUDA: 25.73, INT4 CUDA Speed Up (ORT/PyTorch): 6.34\nBatch Size, Prompt Length: 1, 2048, PyTorch Eager INT4 CUDA: 25.72, INT4 CUDA Speed Up (ORT/PyTorch): 5.24\nBatch Size, Prompt Length: 1, 4096, PyTorch Eager INT4 CUDA: 25.66, INT4 CUDA Speed Up (ORT/PyTorch): 2.97\nBatch Size, Prompt Length: 4, 16, PyTorch Eager INT4 CUDA: 101.31, INT4 CUDA Speed Up (ORT/PyTorch): 2.82\nBatch Size, Prompt Length: 4, 64, PyTorch Eager INT4 CUDA: 101.66, INT4 CUDA Speed Up (ORT/PyTorch): 2.77\nBatch Size, Prompt Length: 4, 256, PyTorch Eager INT4 CUDA: 101.15, INT4 CUDA Speed Up (ORT/PyTorch): 2.64\nBatch Size, Prompt Length: 4, 1024, PyTorch Eager INT4 CUDA: 101.09, INT4 CUDA Speed Up (ORT/PyTorch): 2.20\nBatch Size, Prompt Length: 4, 2048, PyTorch Eager INT4 CUDA: 100.78, INT4 CUDA Speed Up (ORT/PyTorch): 1.84\nBatch Size, Prompt Length: 4, 4096, PyTorch Eager INT4 CUDA: 77.98, INT4 CUDA Speed Up (ORT/PyTorch): 1.62\nBatch Size, Prompt Length: 16, 16, PyTorch Eager INT4 CUDA: 394.19, INT4 CUDA Speed Up (ORT/PyTorch): 2.52\nBatch Size, Prompt Length: 16, 64, PyTorch Eager INT4 CUDA: 394.29, INT4 CUDA Speed Up (ORT/PyTorch): 2.41\nBatch Size, Prompt Length: 16, 256, PyTorch Eager INT4 CUDA: 405.30, INT4 CUDA Speed Up (ORT/PyTorch): 2.00\nBatch Size, Prompt Length: 16, 1024, PyTorch Eager INT4 CUDA: 294.79, INT4 CUDA Speed Up (ORT/PyTorch): 1.79\nBatch Size, Prompt Length: 16, 2048, PyTorch Eager INT4 CUDA: 203.02, INT4 CUDA Speed Up (ORT/PyTorch): 1.81\nBatch Size, Prompt Length: 16, 4096, PyTorch Eager INT4 CUDA: OOM, INT4 CUDA Speed Up (ORT/PyTorch): \n\n\nNote: PyTorch compile and URL currently do not support the Phi-3 Mini-128K-Instruct model.", "### Package Versions\n\n\n\nAppendix\n--------", "### Activation Aware Quantization\n\n\nAWQ works by identifying the top 1% most salient weights that are most important for maintaining accuracy and quantizing the remaining 99% of weights. This leads to less accuracy loss from quantization compared to many other quantization techniques. For more on AWQ, see here.\n\n\nModel Card Contact\n------------------\n\n\nparinitarahi, kvaishnavi, natke\n\n\nContributors\n------------\n\n\nKunal Vaishnavi, Sunghoon Choi, Yufeng Li, Akshay Sonawane, Sheetal Arun Kadam, Rui Ren, Edward Chen, Scott McKay, Ryan Hill, Emma Ning, Natalie Kershaw, Parinita Rahi, Patrice Vignola, Chai Chaoweeraprasit, Logan Iyer, Vicente Rivera, Jacques Van Rhyn" ]

[ "TAGS\n#transformers #onnx #phi3 #text-generation #ONNX #DML #ONNXRuntime #nlp #conversational #custom_code #arxiv-2306.00978 #license-mit #autotrain_compatible #has_space #region-us \n", "### Model Description\n\n\n* Developed by: Microsoft\n* Model type: ONNX\n* Language(s) (NLP): Python, C, C++\n* License: MIT\n* Model Description: This is a conversion of the Phi-3 Mini-4K-Instruct model for ONNX Runtime inference.\n\n\nAdditional Details\n------------------\n\n\n* ONNX Runtime Optimizations Blog Link\n* Phi-3 Model Blog Link\n* Phi-3 Model Card\n* Phi-3 Technical Report\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTo make running of the Phi-3 models across a range of devices and platforms across various execution provider backends possible, we introduce a new API to wrap several aspects of generative AI inferencing. This API make it easy to drag and drop LLMs straight into your app. For running the early version of these models with ONNX Runtime, follow the steps here.\n\n\nFor example:\n\n\nPerformance Metrics\n-------------------\n\n\nPhi-3 Mini-128K-Instruct performs better in ONNX Runtime than PyTorch for all batch size, prompt length combinations. For FP16 CUDA, ORT performs up to 5X faster than PyTorch, while with INT4 CUDA it's up to 9X faster than PyTorch.\n\n\nThe table below shows the average throughput of the first 256 tokens generated (tps) for FP16 and INT4 precisions on CUDA as measured on 1 A100 80GB GPU, SKU: Standard\\_ND96amsr\\_A100\\_v4.\n\n\n\nBatch Size, Prompt Length: 1, 16, PyTorch Eager INT4 CUDA: 25.35, INT4 CUDA Speed Up (ORT/PyTorch): 8.89\nBatch Size, Prompt Length: 1, 64, PyTorch Eager INT4 CUDA: 25.69, INT4 CUDA Speed Up (ORT/PyTorch): 8.58\nBatch Size, Prompt Length: 1, 256, PyTorch Eager INT4 CUDA: 25.77, INT4 CUDA Speed Up (ORT/PyTorch): 7.69\nBatch Size, Prompt Length: 1, 1024, PyTorch Eager INT4 CUDA: 25.73, INT4 CUDA Speed Up (ORT/PyTorch): 6.34\nBatch Size, Prompt Length: 1, 2048, PyTorch Eager INT4 CUDA: 25.72, INT4 CUDA Speed Up (ORT/PyTorch): 5.24\nBatch Size, Prompt Length: 1, 4096, PyTorch Eager INT4 CUDA: 25.66, INT4 CUDA Speed Up (ORT/PyTorch): 2.97\nBatch Size, Prompt Length: 4, 16, PyTorch Eager INT4 CUDA: 101.31, INT4 CUDA Speed Up (ORT/PyTorch): 2.82\nBatch Size, Prompt Length: 4, 64, PyTorch Eager INT4 CUDA: 101.66, INT4 CUDA Speed Up (ORT/PyTorch): 2.77\nBatch Size, Prompt Length: 4, 256, PyTorch Eager INT4 CUDA: 101.15, INT4 CUDA Speed Up (ORT/PyTorch): 2.64\nBatch Size, Prompt Length: 4, 1024, PyTorch Eager INT4 CUDA: 101.09, INT4 CUDA Speed Up (ORT/PyTorch): 2.20\nBatch Size, Prompt Length: 4, 2048, PyTorch Eager INT4 CUDA: 100.78, INT4 CUDA Speed Up (ORT/PyTorch): 1.84\nBatch Size, Prompt Length: 4, 4096, PyTorch Eager INT4 CUDA: 77.98, INT4 CUDA Speed Up (ORT/PyTorch): 1.62\nBatch Size, Prompt Length: 16, 16, PyTorch Eager INT4 CUDA: 394.19, INT4 CUDA Speed Up (ORT/PyTorch): 2.52\nBatch Size, Prompt Length: 16, 64, PyTorch Eager INT4 CUDA: 394.29, INT4 CUDA Speed Up (ORT/PyTorch): 2.41\nBatch Size, Prompt Length: 16, 256, PyTorch Eager INT4 CUDA: 405.30, INT4 CUDA Speed Up (ORT/PyTorch): 2.00\nBatch Size, Prompt Length: 16, 1024, PyTorch Eager INT4 CUDA: 294.79, INT4 CUDA Speed Up (ORT/PyTorch): 1.79\nBatch Size, Prompt Length: 16, 2048, PyTorch Eager INT4 CUDA: 203.02, INT4 CUDA Speed Up (ORT/PyTorch): 1.81\nBatch Size, Prompt Length: 16, 4096, PyTorch Eager INT4 CUDA: OOM, INT4 CUDA Speed Up (ORT/PyTorch): \n\n\nNote: PyTorch compile and URL currently do not support the Phi-3 Mini-128K-Instruct model.", "### Package Versions\n\n\n\nAppendix\n--------", "### Activation Aware Quantization\n\n\nAWQ works by identifying the top 1% most salient weights that are most important for maintaining accuracy and quantizing the remaining 99% of weights. This leads to less accuracy loss from quantization compared to many other quantization techniques. For more on AWQ, see here.\n\n\nModel Card Contact\n------------------\n\n\nparinitarahi, kvaishnavi, natke\n\n\nContributors\n------------\n\n\nKunal Vaishnavi, Sunghoon Choi, Yufeng Li, Akshay Sonawane, Sheetal Arun Kadam, Rui Ren, Edward Chen, Scott McKay, Ryan Hill, Emma Ning, Natalie Kershaw, Parinita Rahi, Patrice Vignola, Chai Chaoweeraprasit, Logan Iyer, Vicente Rivera, Jacques Van Rhyn" ]

[ "mlx", "safetensors", "llama", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# lucataco/Llama-3-8B-16K-8bit\nThis model was converted to MLX format from ['lucataco/Llama-3-8B-16K']() 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 #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# lucataco/Llama-3-8B-16K-8bit\nThis model was converted to MLX format from ['lucataco/Llama-3-8B-16K']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "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: nldemo\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: nldemo\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", "vision-encoder-decoder", "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 #vision-encoder-decoder #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" ]

[ "mlx", "safetensors", "llama", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# mattshumer/Llama-3-8B-16K-4bit\nThis model was converted to MLX format from 'mattshumer/Llama-3-8B-16K' 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 #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# mattshumer/Llama-3-8B-16K-4bit\nThis model was converted to MLX format from 'mattshumer/Llama-3-8B-16K' using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "yanolja/KoSOLAR-10.7B-v0.2", "yanolja/Bookworm-10.7B-v0.4-DPO", "base_model:yanolja/KoSOLAR-10.7B-v0.2", "base_model:yanolja/Bookworm-10.7B-v0.4-DPO", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# solar_merge_test_1", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #yanolja/KoSOLAR-10.7B-v0.2 #yanolja/Bookworm-10.7B-v0.4-DPO #base_model-yanolja/KoSOLAR-10.7B-v0.2 #base_model-yanolja/Bookworm-10.7B-v0.4-DPO #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# solar_merge_test_1", "## Configuration", "## Usage" ]

[ "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: phoenixaiden33/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: phoenixaiden33/ppo-SnowballTarget\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:nvidia/OpenMath-Mistral-7B-v0.1-hf", "license:apache-2.0", "region:us" ]

[]

[]

[ "# OpenMath-Mistral-7B-v0.1-hf-squad2-flash-attention-2\n\nThis model is a fine-tuned version of nvidia/OpenMath-Mistral-7B-v0.1-hf on the generator 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: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\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: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-nvidia/OpenMath-Mistral-7B-v0.1-hf #license-apache-2.0 #region-us \n", "# OpenMath-Mistral-7B-v0.1-hf-squad2-flash-attention-2\n\nThis model is a fine-tuned version of nvidia/OpenMath-Mistral-7B-v0.1-hf on the generator 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: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\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: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[ "en" ]

[ "# 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 #en #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" ]

[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "sft", "en", "base_model:Dogge/llama-3-70B-instruct-uncensored", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #sft #en #base_model-Dogge/llama-3-70B-instruct-uncensored #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "mlx", "safetensors", "llama", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# mattshumer/Llama-3-8B-16K-8bit\nThis model was converted to MLX format from 'mattshumer/Llama-3-8B-16K' 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 #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# mattshumer/Llama-3-8B-16K-8bit\nThis model was converted to MLX format from 'mattshumer/Llama-3-8B-16K' using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "transformers", "safetensors", "mistral", "text-generation", "trl", "sft", "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 #mistral #text-generation #trl #sft #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", "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" ]

[ "gguf", "region:us" ]

[]

[]

[]

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

[ "transformers", "pytorch", "yuan", "text-generation", "conversational", "custom_code", "arxiv:2311.15786", "license:other", "autotrain_compatible", "region:us" ]

[ "2311.15786" ]

[]

[]

[ "TAGS\n#transformers #pytorch #yuan #text-generation #conversational #custom_code #arxiv-2311.15786 #license-other #autotrain_compatible #region-us \n" ]

[ "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" ]

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

[]

[]

[ "# ubitus-whisper-v1.0-medium\n\nThis model is a fine-tuned version of openai/whisper-medium.\nThe original Whisper model wasn't very accurate at translating medical terms.\nWe use the Whisper medium model as the basic model and use medical terminology and clinical records to fine-tune Whisper so that Whisper can correctly translate medical terminology and common consultation conversations between doctors and patients.\nIn addition, since Whisper does not support streaming translation mode, we have also developed an API to allow Whisper to have functions close to streaming translation to improve user experience.", "## 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: 4\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 2\n- total_train_batch_size: 16\n- total_eval_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- mixed_precision_training: Native AMP", "### Framework versions\n\n- Transformers 4.39.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#pytorch #license-apache-2.0 #region-us \n", "# ubitus-whisper-v1.0-medium\n\nThis model is a fine-tuned version of openai/whisper-medium.\nThe original Whisper model wasn't very accurate at translating medical terms.\nWe use the Whisper medium model as the basic model and use medical terminology and clinical records to fine-tune Whisper so that Whisper can correctly translate medical terminology and common consultation conversations between doctors and patients.\nIn addition, since Whisper does not support streaming translation mode, we have also developed an API to allow Whisper to have functions close to streaming translation to improve user experience.", "## 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: 4\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 2\n- total_train_batch_size: 16\n- total_eval_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- mixed_precision_training: Native AMP", "### Framework versions\n\n- Transformers 4.39.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "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" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "transformers", "pytorch", "llama", "text-generation", "arxiv:2307.09288", "arxiv:2306.05685", "license:llama2", "autotrain_compatible", "text-generation-inference", "region:us" ]

[ "2307.09288", "2306.05685" ]

[]

[ "# Vicuna Model Card", "## Model Details\n\nVicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.\n\n- Developed by: LMSYS\n- Model type: An auto-regressive language model based on the transformer architecture\n- License: Llama 2 Community License Agreement\t\n- Finetuned from model: Llama 2", "### Model Sources\n\n- Repository: URL\n- Blog: URL\n- Paper: URL\n- Demo: URL", "## Uses\n\nThe primary use of Vicuna is research on large language models and chatbots.\nThe primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.", "## How to Get Started with the Model\n\n- Command line interface: URL\n- APIs (OpenAI API, Huggingface API): URL", "## Training Details\n\nVicuna v1.5 (16k) is fine-tuned from Llama 2 with supervised instruction fine-tuning and linear RoPE scaling.\nThe training data is around 125K conversations collected from URL. These conversations are packed into sequences that contain 16K tokens each.\nSee more details in the \"Training Details of Vicuna Models\" section in the appendix of this paper.", "## Evaluation\n\n!Evaluation Results\n\nVicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this paper and leaderboard.", "## Difference between different versions of Vicuna\n\nSee vicuna_weights_version.md" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #arxiv-2307.09288 #arxiv-2306.05685 #license-llama2 #autotrain_compatible #text-generation-inference #region-us \n", "# Vicuna Model Card", "## Model Details\n\nVicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.\n\n- Developed by: LMSYS\n- Model type: An auto-regressive language model based on the transformer architecture\n- License: Llama 2 Community License Agreement\t\n- Finetuned from model: Llama 2", "### Model Sources\n\n- Repository: URL\n- Blog: URL\n- Paper: URL\n- Demo: URL", "## Uses\n\nThe primary use of Vicuna is research on large language models and chatbots.\nThe primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.", "## How to Get Started with the Model\n\n- Command line interface: URL\n- APIs (OpenAI API, Huggingface API): URL", "## Training Details\n\nVicuna v1.5 (16k) is fine-tuned from Llama 2 with supervised instruction fine-tuning and linear RoPE scaling.\nThe training data is around 125K conversations collected from URL. These conversations are packed into sequences that contain 16K tokens each.\nSee more details in the \"Training Details of Vicuna Models\" section in the appendix of this paper.", "## Evaluation\n\n!Evaluation Results\n\nVicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this paper and leaderboard.", "## Difference between different versions of Vicuna\n\nSee vicuna_weights_version.md" ]

[ "transformers", "safetensors", "bert", "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 #bert #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" ]

[ "transformers", "pytorch", "llama", "text-generation", "en", "ja", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "ja" ]

[ "### Pre-training\n\n\nThe models have been pre-trained using a blend of the following datasets.", "### Instruction tuning\n\n\nThe models have been fine-tuned on the following datasets.\n\n\n\nEvaluation\n----------\n\n\nYou can view the evaluation results of several LLMs on this leaderboard. We used llm-jp-eval (v1.3.0) for the evaluation.\n\n\nBesides, we used LLM-as-a-judge frameworks, Japanese Vicuna QA Benchmark and Japanese MT Bench, for evaluation.\nFor details, please refer to our technical blog (in Japanese).\n\n\nRisks and Limitations\n---------------------\n\n\nThe models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.\n\n\nSend Questions to\n-----------------\n\n\nllm-jp(at)URL\n\n\nLicense\n-------\n\n\nApache License, Version 2.0\n\n\nModel Card Authors\n------------------\n\n\n*The names are listed in alphabetical order.*\n\n\nNamgi Han, Tatsuya Hiraoka, Hirokazu Kiyomaru, Takashi Kodama, and Hiroshi Matsuda." ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #en #ja #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us \n", "### Pre-training\n\n\nThe models have been pre-trained using a blend of the following datasets.", "### Instruction tuning\n\n\nThe models have been fine-tuned on the following datasets.\n\n\n\nEvaluation\n----------\n\n\nYou can view the evaluation results of several LLMs on this leaderboard. We used llm-jp-eval (v1.3.0) for the evaluation.\n\n\nBesides, we used LLM-as-a-judge frameworks, Japanese Vicuna QA Benchmark and Japanese MT Bench, for evaluation.\nFor details, please refer to our technical blog (in Japanese).\n\n\nRisks and Limitations\n---------------------\n\n\nThe models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.\n\n\nSend Questions to\n-----------------\n\n\nllm-jp(at)URL\n\n\nLicense\n-------\n\n\nApache License, Version 2.0\n\n\nModel Card Authors\n------------------\n\n\n*The names are listed in alphabetical order.*\n\n\nNamgi Han, Tatsuya Hiraoka, Hirokazu Kiyomaru, Takashi Kodama, and Hiroshi Matsuda." ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.01_ablation_4iters_bs256_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_ablation_4iters_bs256_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_4iters_bs256_iter_2 on the updated and the original datasets.", "## 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-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.01_ablation_4iters_bs256_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_ablation_4iters_bs256_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_4iters_bs256_iter_2 on the updated and the original datasets.", "## 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-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]