chore: add model featured

all.json

@@ -1 +1 @@
-{"_version": "1", "created_at": "2023-12-21T12:01:09.487890Z", "updated_at": "2023-12-21T12:01:09.489062Z", "models": [{"_version": "1.0.0", "name": "llama2-7b-chat-hf", "creator": "meta-llama", "title": "Llama 2 7B Chat", "version": "2.0.0", "summary": "Llama 2 7B Chat is a large language model fine-tuned for dialogue use cases.", "description": "Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.", "author": "AI Research by Meta", "publisher": {"name": "meta-llama", "url": "https://huggingface.co/meta-llama"}, "license": {"name": "Meta Research License Agreement v1.0"}, "tags": "llama llama2 facebook meta english", "task_type": ["conversational"], "languages": ["en"], "model_size": "7b", "context_size": 1024, "tensor_type": "float32", "base_model": "none", "model_type": "llama", "library": "PyTorch", "private": true, "use_cases": " Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.", "out_of_scope_use_cases": "Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.", "bias_risks_limitations": "Llama-2-Chat models are trained on a large corpus of English text, which may contain bias. We recommend that you evaluate the model for your use case before deploying it.", "repository": "https://huggingface.co/meta-llama/Llama-2-7b-chat-hf", "download": "https://huggingface.co/meta-llama/Llama-2-7b-chat-hf", "paper": "https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/", "include": [{"name": "Llama-2-7B-Chat-GGML", "release_date": "2021-10-01", "publisher": {"name": "TheBloke", "url": "https://huggingface.co/TheBloke"}, "description": "This repo contains GGUF format model files for Meta Llama 2's Llama 2 7B Chat.", "base_model": "meta-llama/llama-2-7b-chat-hf", "model_type": "llama", "library": "GGML", "repository": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q2_K.gguf", "include": [{"name": "llama-2-7b-chat.Q2_K.gguf", "use_case": "smallest, significant quality loss - not recommended for most purposes", "quantization": "Q2_K", "bits": 2, "size": 2.83, "max_ram": 5.33, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q2_K.gguf"}, {"name": "llama-2-7b-chat.Q3_K_S.gguf", "recommandations": "very small, high quality loss", "quantization": "Q3_K_S", "bits": 3, "size": 2.95, "max_ram": 5.45, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_S.gguf"}, {"name": "llama-2-7b-chat.Q3_K_M.gguf", "recommandations": "very small, high quality loss", "quantization": "Q3_K_M", "bits": 3, "size": 3.3, "max_ram": 5.8, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_M.gguf"}, {"name": "llama-2-7b-chat.Q3_K_L.gguf", "recommandations": "small, substantial quality loss", "quantization": "Q3_K_L", "bits": 3, "size": 3.6, "max_ram": 6.1, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_L.gguf"}, {"name": "llama-2-7b-chat.Q4_0.gguf", "recommandations": "legacy; small, very high quality loss - prefer using Q3_K_M", "quantization": "Q4_0", "bits": 4, "size": 3.83, "max_ram": 6.33, "deprecated": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_0.gguf"}, {"name": "llama-2-7b-chat.Q4_K_S.gguf", "recommandations": "small, greater quality loss", "quantization": "Q4_K_S", "bits": 4, "size": 3.86, "max_ram": 6.36, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_S.gguf"}, {"name": "llama-2-7b-chat.Q4_K_M.gguf", "recommandations": "medium, balanced quality - recommended", "quantization": "Q4_K_M", "bits": 4, "size": 4.08, "max_ram": 6.58, "recommended": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf"}, {"name": "llama-2-7b-chat.Q5_0.gguf", "recommandations": "legacy; medium, balanced quality - prefer using Q4_K_M", "quantization": "Q5_0", "bits": 5, "size": 4.65, "max_ram": 7.15, "deprecated": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_0.gguf"}, {"name": "llama-2-7b-chat.Q5_K_S.gguf", "recommandations": "large, low quality loss - recommended", "quantization": "Q5_K_S", "bits": 5, "size": 4.65, "max_ram": 7.15, "recommended": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_K_S.gguf"}, {"name": "llama-2-7b-chat.Q5_K_M.gguf", "recommandations": "large, very low quality loss - recommended", "quantization": "Q5_K_M", "bits": 5, "size": 4.78, "max_ram": 7.28, "recommended": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_K_M.gguf"}, {"name": "llama-2-7b-chat.Q6_K.gguf", "recommandations": "very large, extremely low quality loss", "quantization": "Q6_K", "bits": 6, "size": 5.53, "max_ram": 8.03, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q6_K.gguf"}, {"name": "llama-2-7b-chat.Q8_0.gguf", "recommandations": "very large, extremely low quality loss", "quantization": "Q8_0", "bits": 8, "size": 7.16, "max_ram": 9.66, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q8_0.gguf"}]}]}]}
+{"_version": "1", "created_at": "2023-12-21T14:48:08.996688Z", "updated_at": "2023-12-21T14:48:08.999456Z", "models": [{"_version": "1.0.0", "name": "llama2-7b-chat-hf", "creator": "meta-llama", "title": "Llama 2 7B Chat", "version": "2.0.0", "summary": "Llama 2 7B Chat is a large language model fine-tuned for dialogue use cases.", "description": "Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.", "author": "AI Research by Meta", "publisher": {"name": "meta-llama", "url": "https://huggingface.co/meta-llama"}, "license": {"name": "Meta Research License Agreement v1.0"}, "tags": "llama llama2 facebook meta english", "task_type": ["conversational"], "languages": ["en"], "model_size": "7b", "context_size": 1024, "tensor_type": "float32", "base_model": "none", "model_type": "llama", "library": "PyTorch", "private": true, "featured": true, "use_cases": " Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.", "out_of_scope_use_cases": "Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.", "bias_risks_limitations": "Llama-2-Chat models are trained on a large corpus of English text, which may contain bias. We recommend that you evaluate the model for your use case before deploying it.", "repository": "https://huggingface.co/meta-llama/Llama-2-7b-chat-hf", "download": "https://huggingface.co/meta-llama/Llama-2-7b-chat-hf", "paper": "https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/", "include": [{"name": "Llama-2-7B-Chat-GGML", "release_date": "2021-10-01", "publisher": {"name": "TheBloke", "url": "https://huggingface.co/TheBloke"}, "description": "This repo contains GGUF format model files for Meta Llama 2's Llama 2 7B Chat.", "base_model": "meta-llama/llama-2-7b-chat-hf", "model_type": "llama", "library": "GGML", "repository": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q2_K.gguf", "include": [{"name": "llama-2-7b-chat.Q2_K.gguf", "use_case": "smallest, significant quality loss - not recommended for most purposes", "quantization": "Q2_K", "bits": 2, "size": 2.83, "max_ram": 5.33, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q2_K.gguf"}, {"name": "llama-2-7b-chat.Q3_K_S.gguf", "recommandations": "very small, high quality loss", "quantization": "Q3_K_S", "bits": 3, "size": 2.95, "max_ram": 5.45, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_S.gguf"}, {"name": "llama-2-7b-chat.Q3_K_M.gguf", "recommandations": "very small, high quality loss", "quantization": "Q3_K_M", "bits": 3, "size": 3.3, "max_ram": 5.8, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_M.gguf"}, {"name": "llama-2-7b-chat.Q3_K_L.gguf", "recommandations": "small, substantial quality loss", "quantization": "Q3_K_L", "bits": 3, "size": 3.6, "max_ram": 6.1, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q3_K_L.gguf"}, {"name": "llama-2-7b-chat.Q4_0.gguf", "recommandations": "legacy; small, very high quality loss - prefer using Q3_K_M", "quantization": "Q4_0", "bits": 4, "size": 3.83, "max_ram": 6.33, "deprecated": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_0.gguf"}, {"name": "llama-2-7b-chat.Q4_K_S.gguf", "recommandations": "small, greater quality loss", "quantization": "Q4_K_S", "bits": 4, "size": 3.86, "max_ram": 6.36, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_S.gguf"}, {"name": "llama-2-7b-chat.Q4_K_M.gguf", "recommandations": "medium, balanced quality - recommended", "quantization": "Q4_K_M", "bits": 4, "size": 4.08, "max_ram": 6.58, "recommended": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf"}, {"name": "llama-2-7b-chat.Q5_0.gguf", "recommandations": "legacy; medium, balanced quality - prefer using Q4_K_M", "quantization": "Q5_0", "bits": 5, "size": 4.65, "max_ram": 7.15, "deprecated": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_0.gguf"}, {"name": "llama-2-7b-chat.Q5_K_S.gguf", "recommandations": "large, low quality loss - recommended", "quantization": "Q5_K_S", "bits": 5, "size": 4.65, "max_ram": 7.15, "recommended": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_K_S.gguf"}, {"name": "llama-2-7b-chat.Q5_K_M.gguf", "recommandations": "large, very low quality loss - recommended", "quantization": "Q5_K_M", "bits": 5, "size": 4.78, "max_ram": 7.28, "recommended": true, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q5_K_M.gguf"}, {"name": "llama-2-7b-chat.Q6_K.gguf", "recommandations": "very large, extremely low quality loss", "quantization": "Q6_K", "bits": 6, "size": 5.53, "max_ram": 8.03, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q6_K.gguf"}, {"name": "llama-2-7b-chat.Q8_0.gguf", "recommandations": "very large, extremely low quality loss", "quantization": "Q8_0", "bits": 8, "size": 7.16, "max_ram": 9.66, "download": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q8_0.gguf"}]}]}]}

models/meta-llama/llama-2-7b-chat-hf.json

@@ -27,6 +27,7 @@
     "model_type": "llama",
     "library": "PyTorch",
     "private": true,
+    "featured": true,
     "use_cases": " Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.",
     "out_of_scope_use_cases": "Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.",
     "bias_risks_limitations": "Llama-2-Chat models are trained on a large corpus of English text, which may contain bias. We recommend that you evaluate the model for your use case before deploying it.",

schema/v1/model.schema.json

@@ -116,6 +116,10 @@
                     "type": "boolean",
                     "description": "The model is private"
                 },
+                "featured": {
+                    "type": "boolean",
+                    "description": "The model is featured"
+                },
                 "model_type": {
                     "type": "string",
                     "description": "The type of the model",