Is this model support function call
I got the response status = 200, but the finish_reason is error, but return finish_reason = 'tool_calls' while I use Ollama on my laptop
{'id': 'chatcmpl-a6d5a08029f4468eb289a54c8eb6ecd3', 'choices': [{'finish_reason': 'error', 'index': 0, 'message': {'content': "I don't have real-time data access, so I can't provide the current weather in Pittsburgh, PA right now. You can check the current weather by using a weather website or app such as the Weather Channel, AccuWeather, or another trusted source. These platforms will give you the most accurate and up-to-date information.", 'role': 'assistant', 'name': None, 'tool_calls': None, 'tool_call_id': None}, 'logprobs': None}], 'created': 1732783200, 'model': '/root/llm/Qwen2.5-32B-Instruct-q4f16_1-MLC/', 'system_fingerprint': '', 'object': 'chat.completion', 'usage': {'prompt_tokens': 32, 'completion_tokens': 67, 'total_tokens': 99, 'extra': None}}
My Server env is :
- anaconda python 3.12
- MLC-LLM CUDA 12.3 prebuild package