Update app.py

app.py

@@ -19,6 +19,6 @@ class GenerateResponse(BaseModel):
 @app.post("/generate/qwen3-0.6b-gguf", response_model=GenerateResponse)
 async def generate_qwen3_gguf_endpoint(request: PromptRequest):
     messages = [{"role": "user", "content": request.prompt}]
-    response = qwen3_gguf_llm.create_chat_completion(messages=messages, max_tokens=256)
+    response = qwen3_gguf_llm.create_chat_completion(messages=messages)
     generated_text = response['choices'][0]['message']['content']
     return GenerateResponse(generated_text=generated_text)