feat(model): Support Qwen2.5 models

README.ja.md

@@ -154,6 +154,15 @@ DB-GPTのアーキテクチャは以下の図に示されています：
   私たちは、LLaMA/LLaMA2、Baichuan、ChatGLM、Wenxin、Tongyi、Zhipuなど、オープンソースおよびAPIエージェントからの数十の大規模言語モデル（LLM）を含む幅広いモデルをサポートしています。
 
   - ニュース
+    - 🔥🔥🔥  [Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)

README.md

@@ -168,6 +168,15 @@ 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
+    - 🔥🔥🔥  [Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)

README.zh.md

@@ -163,6 +163,15 @@
   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
+    - 🔥🔥🔥  [Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
+    - 🔥🔥🔥  [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
     - 🔥🔥🔥  [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)

dbgpt/configs/model_config.py

@@ -173,6 +173,17 @@ def get_device() -> str:
     "qwen2-0.5b-instruct-gptq-int4": os.path.join(
         MODEL_PATH, "Qwen2-0.5B-Instruct-GPTQ-Int4"
     ),
+    "qwen2.5-0.5b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-0.5B-Instruct"),
+    "qwen2.5-1.5b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-1.5B-Instruct"),
+    "qwen2.5-3b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-3B-Instruct"),
+    "qwen2.5-7b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-7B-Instruct"),
+    "qwen2.5-14b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-14B-Instruct"),
+    "qwen2.5-32b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-32B-Instruct"),
+    "qwen2.5-72b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-72B-Instruct"),
+    "qwen2.5-coder-1.5b-instruct": os.path.join(
+        MODEL_PATH, "Qwen2.5-Coder-1.5B-Instruct"
+    ),
+    "qwen2.5-coder-7b-instruct": os.path.join(MODEL_PATH, "Qwen2.5-Coder-7B-Instruct"),
     # (Llama2 based) We only support WizardLM-13B-V1.2 for now, which is trained from Llama-2 13b, see https://huggingface.co/WizardLM/WizardLM-13B-V1.2
     "wizardlm-13b": os.path.join(MODEL_PATH, "WizardLM-13B-V1.2"),
     # wget https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/resolve/main/vicuna-13b-v1.5.Q4_K_M.gguf -O models/ggml-model-q4_0.gguf

dbgpt/model/adapter/hf_adapter.py

@@ -370,10 +370,15 @@ class Qwen2Adapter(QwenAdapter):
     support_8bit: bool = True
 
     def do_match(self, lower_model_name_or_path: Optional[str] = None):
-        return (
-            lower_model_name_or_path
-            and "qwen2" in lower_model_name_or_path
-            and "instruct" in lower_model_name_or_path
+        return lower_model_name_or_path and (
+            (
+                "qwen2" in lower_model_name_or_path
+                and "instruct" in lower_model_name_or_path
+            )
+            or (
+                "qwen2.5" in lower_model_name_or_path
+                and "instruct" in lower_model_name_or_path
+            )
         )