Talking to Mistral-Nemo via OpenAI tool calling - fails

### What is the issue? With this curl command: ``` curl http://localhost:11434/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model":"mistral-nemo:12b-instruct-2407-fp16", "messages": [ { "role": "user", "content": "What is the weather like in Boston?" } ], "tools": [ { "type": "function", "function": { "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"] } } } ], "tool_choice": "auto" }' | json_pp ``` we should be able to execute an OpenAI API compatible tool use call against `mistral-nemo`. But I get this result: ``` { "choices" : [ { "finish_reason" : "stop", "index" : 0, "message" : { "content" : "Glad to help! In which unit would you like the temperature?", "role" : "assistant" } } ], "created" : 1725905432, "id" : "chatcmpl-677", "model" : "mistral-nemo:12b-instruct-2407-fp16", "object" : "chat.completion", "system_fingerprint" : "fp_ollama", "usage" : { "completion_tokens" : 15, "prompt_tokens" : 95, "total_tokens" : 110 } } ``` Is there a missing config or something similar like that? Thanks. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.3.9