feat(model): Support Mixtral-8x7B (eosphoros-ai#959)

README.md

@@ -103,7 +103,8 @@ At present, we have introduced several key features to showcase our current capa
   We offer extensive model support, including dozens of large language models (LLMs) from both open-source and API agents, such as LLaMA/LLaMA2, Baichuan, ChatGLM, Wenxin, Tongyi, Zhipu, and many more. 
 
   - News
-    - 🔥🔥🔥  [qwen-72b-chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
+    - 🔥🔥🔥  [Mixtral-8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
+    - 🔥🔥🔥  [Qwen-72B-Chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
     - 🔥🔥🔥  [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)
   - [More Supported LLMs](http://docs.dbgpt.site/docs/modules/smmf)
 

README.zh.md

@@ -111,7 +111,8 @@ DB-GPT是一个开源的数据库领域大模型框架。目的是构建大模
   海量模型支持，包括开源、API代理等几十种大语言模型。如LLaMA/LLaMA2、Baichuan、ChatGLM、文心、通义、智谱等。当前已支持如下模型: 
 
   - 新增支持模型
-    - 🔥🔥🔥  [qwen-72b-chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
+    - 🔥🔥🔥  [Mixtral-8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
+    - 🔥🔥🔥  [Qwen-72B-Chat](https://huggingface.co/Qwen/Qwen-72B-Chat)
     - 🔥🔥🔥  [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)
   - [更多开源模型](https://www.yuque.com/eosphoros/dbgpt-docs/iqaaqwriwhp6zslc#qQktR)
 

dbgpt/app/chat_adapter.py

@@ -245,7 +245,7 @@ def get_conv_template(self, model_path: str) -> Conversation:
 
 class LlamaCppChatAdapter(BaseChatAdpter):
     def match(self, model_path: str):
-        from dbgpt.model.adapter import LlamaCppAdapater
+        from dbgpt.model.adapter.old_adapter import LlamaCppAdapater
 
         if "llama-cpp" == model_path:
             return True

dbgpt/configs/model_config.py

@@ -113,7 +113,9 @@ def get_device() -> str:
     # https://huggingface.co/microsoft/Orca-2-13b
     "orca-2-13b": os.path.join(MODEL_PATH, "Orca-2-13b"),
     # https://huggingface.co/openchat/openchat_3.5
-    "openchat_3.5": os.path.join(MODEL_PATH, "openchat_3.5"),
+    "openchat-3.5": os.path.join(MODEL_PATH, "openchat_3.5"),
+    # https://huggingface.co/openchat/openchat-3.5-1210
+    "openchat-3.5-1210": os.path.join(MODEL_PATH, "openchat-3.5-1210"),
     # https://huggingface.co/hfl/chinese-alpaca-2-7b
     "chinese-alpaca-2-7b": os.path.join(MODEL_PATH, "chinese-alpaca-2-7b"),
     # https://huggingface.co/hfl/chinese-alpaca-2-13b
@@ -124,6 +126,10 @@ def get_device() -> str:
     "zephyr-7b-alpha": os.path.join(MODEL_PATH, "zephyr-7b-alpha"),
     # https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
     "mistral-7b-instruct-v0.1": os.path.join(MODEL_PATH, "Mistral-7B-Instruct-v0.1"),
+    # https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+    "mixtral-8x7b-instruct-v0.1": os.path.join(
+        MODEL_PATH, "Mixtral-8x7B-Instruct-v0.1"
+    ),
     # https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca
     "mistral-7b-openorca": os.path.join(MODEL_PATH, "Mistral-7B-OpenOrca"),
     # https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1