Has anyone successfully fine tuned it for function calling? Thinking could use a lightweight model like this to interpret args in a pipeline then format them for passing down the chain
brew install ollama
brew services start ollama
curl http://localhost:11434/api/generate -d '{
"model": "phi:2.7b-chat-v2-q5_K_M",
"prompt": "Generate a JSON object that models a list of products",
"raw": true, "format": "json",
"stream": false
}' | jq