Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,8 @@
-FROM python:3.9
-RUN pwd
+FROM python:3.11-slim
 WORKDIR $HOME/app
-COPY . .
-RUN mkdir -p /.cache && chmod -R 777 /.cache
-RUN pwd
-RUN ls
-RUN pip install setuptools_scm
-RUN pip install --upgrade wheel
-RUN pip install sphinxcontrib-wavedrom
-# RUN pip install wavedrom --no-build-isolation
-# RUN pip install wavedrom==2.0.3.post3
+COPY requirements.txt $HOME/app
+RUN mkdir /.cache && chmod 777 /.cache
 RUN pip install -r requirements.txt
-VOLUME /data
+COPY . $HOME/app
 EXPOSE 23333
 CMD ["python", "-m", "apis.chat_api"]

apis/chat_api.py

@@ -65,8 +65,8 @@ class ChatAPIApp:
 
     class ChatCompletionsPostItem(BaseModel):
         model: str = Field(
-            default="Mixtral-8x7B-Instruct-v0.1",
-            description="(str) `Mixtral-8x7B-Instruct-v0.1`",
+            default="nous-mixtral-8x7b",
+            description="(str) `nous-mixtral-8x7b`",
         )
         messages: list = Field(
             default=[{"role": "user", "content": "Hello, who are you?"}],

constants/models.py

@@ -1,35 +1,15 @@
 MODEL_MAP = {
-  "mixtral-8x7b": "mistralai/Mixtral-8x7B-Instruct-v0.1",
-  "default": "meta-llama/Llama-3.3-70B-Instruct",
-  "Llama-3.3-70B-Instruct": "meta-llama/Llama-3.3-70B-Instruct",
-  "Qwen2.5-72B-Instruct": "Qwen/Qwen2.5-72B-Instruct",
-  "c4ai-command-r-plus-08-2024": "CohereForAI/c4ai-command-r-plus-08-2024",
-  "DeepSeek-R1-Distill-Qwen-32B": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-  "Llama-3.1-Nemotron-70B-Instruct-HF": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
-  "QwQ-32B-Preview": "Qwen/QwQ-32B-Preview",
-  "Qwen2.5-Coder-32B-Instruct": "Qwen/Qwen2.5-Coder-32B-Instruct",
-  "Llama-3.2-11B-Vision-Instruct": "meta-llama/Llama-3.2-11B-Vision-Instruct",
-  "Hermes-3-Llama-3.1-8B": "NousResearch/Hermes-3-Llama-3.1-8B",
-  "Mistral-Nemo-Instruct-2407": "mistralai/Mistral-Nemo-Instruct-2407",
-  "Phi-3.5-mini-instruct": "microsoft/Phi-3.5-mini-instruct",
-  "DeepSeek-V3-0324": "deepseek-ai/DeepSeek-V3-0324",
+    "mixtral-8x7b": "mistralai/Mixtral-8x7B-Instruct-v0.1",  # [Recommended]
     "nous-mixtral-8x7b": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
     "mistral-7b": "mistralai/Mistral-7B-Instruct-v0.2",
     "yi-1.5-34b": "01-ai/Yi-1.5-34B-Chat",
     "gemma-7b": "google/gemma-1.1-7b-it",
+    # "openchat-3.5": "openchat/openchat-3.5-0106",
+    # "command-r-plus": "CohereForAI/c4ai-command-r-plus",
+    # "llama3-70b": "meta-llama/Meta-Llama-3-70B-Instruct",
+    # "zephyr-141b": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
+    "default": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
 }
-# {
-#     "mixtral-8x7b": "mistralai/Mixtral-8x7B-Instruct-v0.1",  # [Recommended]
-#     "nous-mixtral-8x7b": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
-#     "mistral-7b": "mistralai/Mistral-7B-Instruct-v0.2",
-#     "yi-1.5-34b": "01-ai/Yi-1.5-34B-Chat",
-#     "gemma-7b": "google/gemma-1.1-7b-it",
-#     # "openchat-3.5": "openchat/openchat-3.5-0106",
-#     # "command-r-plus": "CohereForAI/c4ai-command-r-plus",
-#     # "llama3-70b": "meta-llama/Meta-Llama-3-70B-Instruct",
-#     # "zephyr-141b": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
-#     "default": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
-# }
 
 AVAILABLE_MODELS = list(MODEL_MAP.keys())
 
@@ -46,16 +26,6 @@ STOP_SEQUENCES_MAP = {
     "yi-1.5-34b": "<|im_end|>",
     # https://huggingface.co/google/gemma-1.1-7b-it/blob/main/tokenizer_config.json#L1509
     "gemma-7b": "<eos>",
-    # https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated/blob/fa13334669544bab573e0e5313cad629a9c02e2c/tokenizer_config.json#L2055
-    "Llama-3.3-70B-Instruct": "<|eot_id|>",
-    # https://huggingface.co/google/gemma-1.1-7b-it/blob/main/tokenizer_config.json#L1509
-    "c4ai-command-r-plus-08-2024": "<|END_OF_TURN_TOKEN|>",
-    # https://huggingface.co/unsloth/Qwen2.5-72B-Instruct/blob/main/tokenizer_config.json
-    "Qwen2.5-72B-Instruct":"<|im_end|>",
-    # https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B/blob/main/tokenizer_config.json
-    "DeepSeek-R1-Distill-Qwen-32B":"<｜end▁of▁sentence｜>",
-    "DeepSeek-V3-0324":"<｜end▁of▁sentence｜>",
-
     # "openchat-3.5": "<|end_of_turn|>",
     # "command-r-plus": "<|END_OF_TURN_TOKEN|>",
 }
@@ -66,12 +36,6 @@ TOKEN_LIMIT_MAP = {
     "mistral-7b": 32768,
     "yi-1.5-34b": 4096,
     "gemma-7b": 8192,
-    "Llama-3.3-70B-Instruct": 131072,
-    "c4ai-command-r-plus-08-2024":1000000000000000019884624838656,
-    "Qwen2.5-72B-Instruct":131072,
-    "DeepSeek-R1-Distill-Qwen-32B":131072,
-    "DeepSeek-R1-Distill-Qwen-32B":131072,
-
     # "openchat-3.5": 8192,
     # "command-r-plus": 32768,
     # "llama3-70b": 8192,
@@ -84,131 +48,74 @@ TOKEN_RESERVED = 20
 
 # https://platform.openai.com/docs/api-reference/models/list
 AVAILABLE_MODELS_DICTS = [
-  {
-    "id": "Llama-3.3-70B-Instruct",
-    "description": "[meta-llama/Llama-3.3-70B-Instruct]: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "meta-llama"
-  },
-  {
-    "id": "Qwen2.5-72B-Instruct",
-    "description": "[Qwen/Qwen2.5-72B-Instruct]: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "Qwen"
-  },
-  {
-    "id": "c4ai-command-r-plus-08-2024",
-    "description": "[CohereForAI/c4ai-command-r-plus-08-2024]: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "CohereForAI"
-  },
-  {
-    "id": "DeepSeek-R1-Distill-Qwen-32B",
-    "description": "[deepseek-ai/DeepSeek-R1-Distill-Qwen-32B]: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "deepseek-ai"
-  },
-  },
-  {
-    "id": "DeepSeek-V3-0324",
-    "description": "[deepseek-ai/DeepSeek-V3-0324]: https://huggingface.co/deepseek-ai/DeepSeek-V3-0324",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "deepseek-ai"
-  },
-  {
-    "id": "Llama-3.1-Nemotron-70B-Instruct-HF",
-    "description": "[nvidia/Llama-3.1-Nemotron-70B-Instruct-HF]: https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "nvidia"
-  },
-  {
-    "id": "QwQ-32B-Preview",
-    "description": "[Qwen/QwQ-32B-Preview]: https://huggingface.co/Qwen/QwQ-32B-Preview",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "Qwen"
-  },
-  {
-    "id": "Qwen2.5-Coder-32B-Instruct",
-    "description": "[Qwen/Qwen2.5-Coder-32B-Instruct]: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "Qwen"
-  },
-  {
-    "id": "Llama-3.2-11B-Vision-Instruct",
-    "description": "[meta-llama/Llama-3.2-11B-Vision-Instruct]: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "meta-llama"
-  },
-  {
-    "id": "Hermes-3-Llama-3.1-8B",
-    "description": "[NousResearch/Hermes-3-Llama-3.1-8B]: https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "NousResearch"
-  },
-  {
-    "id": "Mistral-Nemo-Instruct-2407",
-    "description": "[mistralai/Mistral-Nemo-Instruct-2407]: https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "mistralai"
-  },
-  {
-    "id": "Phi-3.5-mini-instruct",
-    "description": "[microsoft/Phi-3.5-mini-instruct]: https://huggingface.co/microsoft/Phi-3.5-mini-instruct",
-    "object": "model",
-    "created": 1700000000,
-    "owned_by": "microsoft"
-  }
-]
-
-
-'''
-https://huggingface.co/chat/models
-var links = document.querySelectorAll('div.relative a');
-var mlist=[];
-links.forEach(link=>{
-  mlist.push(link.href.split('https://huggingface.co/chat/models/')[1])
-})
-
-p_MODEL_MAP(mlist);
-p_AVAILABLE_MODELS_DICTS(mlist);
-
-
-function p_MODEL_MAP(mlist){
-  let d = {}
-  mlist.forEach(m=>{
-    d[m.split('/')[1]]=m
-  });
-  console.log(d)
-  return d
-}
-
-
-
-function p_AVAILABLE_MODELS_DICTS(mlist){
-  let d = []
-  mlist.forEach(m=>{
-    d.push({
-        "id": m.split('/')[1],
-        "description": `[${m}]: https://huggingface.co/${m}`,
+    {
+        "id": "mixtral-8x7b",
+        "description": "[mistralai/Mixtral-8x7B-Instruct-v0.1]: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1",
         "object": "model",
         "created": 1700000000,
-        "owned_by": m.split('/')[0],
-    },)
-     
-  });
-  console.log(d)
-  return d
-}
-
-'''
+        "owned_by": "mistralai",
+    },
+    {
+        "id": "nous-mixtral-8x7b",
+        "description": "[NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO]: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+        "object": "model",
+        "created": 1700000000,
+        "owned_by": "NousResearch",
+    },
+    {
+        "id": "mistral-7b",
+        "description": "[mistralai/Mistral-7B-Instruct-v0.2]: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2",
+        "object": "model",
+        "created": 1700000000,
+        "owned_by": "mistralai",
+    },
+    {
+        "id": "yi-1.5-34b",
+        "description": "[01-ai/Yi-1.5-34B-Chat]: https://huggingface.co/01-ai/Yi-1.5-34B-Chat",
+        "object": "model",
+        "created": 1700000000,
+        "owned_by": "01-ai",
+    },
+    {
+        "id": "gemma-7b",
+        "description": "[google/gemma-1.1-7b-it]: https://huggingface.co/google/gemma-1.1-7b-it",
+        "object": "model",
+        "created": 1700000000,
+        "owned_by": "Google",
+    },
+    # {
+    #     "id": "openchat-3.5",
+    #     "description": "[openchat/openchat-3.5-0106]: https://huggingface.co/openchat/openchat-3.5-0106",
+    #     "object": "model",
+    #     "created": 1700000000,
+    #     "owned_by": "openchat",
+    # },
+    # {
+    #     "id": "command-r-plus",
+    #     "description": "[CohereForAI/c4ai-command-r-plus]: https://huggingface.co/CohereForAI/c4ai-command-r-plus",
+    #     "object": "model",
+    #     "created": 1700000000,
+    #     "owned_by": "CohereForAI",
+    # },
+    # {
+    #     "id": "llama3-70b",
+    #     "description": "[meta-llama/Meta-Llama-3-70B]: https://huggingface.co/meta-llama/Meta-Llama-3-70B",
+    #     "object": "model",
+    #     "created": 1700000000,
+    #     "owned_by": "Meta",
+    # },
+    # {
+    #     "id": "zephyr-141b",
+    #     "description": "[HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1]: https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
+    #     "object": "model",
+    #     "created": 1700000000,
+    #     "owned_by": "Huggingface",
+    # },
+    # {
+    #     "id": "gpt-3.5-turbo",
+    #     "description": "[openai/gpt-3.5-turbo]: https://platform.openai.com/docs/models/gpt-3-5-turbo",
+    #     "object": "model",
+    #     "created": 1700000000,
+    #     "owned_by": "OpenAI",
+    # },
+]

networks/huggingchat_streamer.py

@@ -20,7 +20,7 @@ class HuggingchatRequester:
         if model in MODEL_MAP.keys():
             self.model = model
         else:
-            self.model = "Llama-3.3-70B-Instruct"
+            self.model = "nous-mixtral-8x7b"
         self.model_fullname = MODEL_MAP[self.model]
 
     def get_hf_chat_id(self):

requirements.txt

@@ -15,5 +15,4 @@ tclogger
 tiktoken
 transformers
 uvicorn
-websockets
-# wavedrom==2.0.3
+websockets