Update app.py

app.py

@@ -24,7 +24,7 @@ TOKEN = os.getenv("HF_TOKEN")
 def load_embedding_mode():
     # embedding_model_dict = {"m3e-base": "/home/xiongwen/m3e-base"}
     encode_kwargs = {"normalize_embeddings": False}
-    model_kwargs = {"device": 'cuda'}
+    model_kwargs = {"device": 'cpu'}
     return HuggingFaceEmbeddings(model_name="BAAI/bge-m3",
                                  model_kwargs=model_kwargs,
                                  encode_kwargs=encode_kwargs)
@@ -81,7 +81,7 @@ retriever = db.as_retriever()
 def langchain_chat(message, temperature, top_p, max_tokens):
     llm = ChatOpenAI(
         # model="meta-llama/Meta-Llama-3-8B-Instruct",
-        model="Qwen/Qwen2-7B-Instruct",
+        model="Qwen/Qwen1.5-4B-Chat",
         temperature=temperature,
         top_p=top_p,
         max_tokens=max_tokens)
@@ -134,7 +134,7 @@ def respond(
     
     for message in  client.chat.completions.create(
         # model="meta-llama/Meta-Llama-3-8B-Instruct",
-        model="Qwen/Qwen2-7B-Instruct",
+        model="Qwen/Qwen1.5-4B-Chat",
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,