google

/

gemma-7b

like 2.98k

The openai chatgpt can make function call,

but gemma-7b not able to understand function call.

please add it.

See: https://platform.openai.com/docs/guides/function-calling

and the basic test:

curl --location 'http://localhost:11434/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
  "model": "gemma:7b-instruct",
  "messages": [
    {"role": "user", "content": "What is the weather like in Boston?"}
  ],
  "functions": [
    {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA"
          },
          "unit": {
            "type": "string",
            "enum": ["celsius", "fahrenheit"]
          }
        },
        "required": ["location"]
      }
    }
  ]
}'

wish result:

ChatCompletionMessage(content='{\n  "location": "Toronto, Canada",\n  "format": "celsius"\n}', role='assistant', function_call=None, tool_calls=None)

what really result

{
    "id": "chatcmpl-83",
    "object": "chat.completion",
    "created": 1708677811,
    "model": "gemma:7b-instruct",
    "system_fingerprint": "fp_ollama",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "I do not have access to real-time information, therefore I cannot provide you with the current weather conditions in Boston. However, you can check a website like weather.com or your local news station for the most up-to-date information."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 17,
        "completion_tokens": 51,
        "total_tokens": 68
    }
}