logoalt Hacker News

ch_smyesterday at 7:46 PM2 repliesview on HN

gemma4 has a specific problem with toolcalls that affects most runtimes. fixes for ollama and vllm are being worked on right now


Replies

adrian_byesterday at 8:44 PM

The chat templates of all Gemma 4 models have been updated 7 days ago, to fix some bugs related to invoking tools.

So any tests done with models that have not been updated during the last days are no longer relevant and they must be repeated after updating the models and regenerating any other file formats, like GGUF files.

apexalphayesterday at 8:28 PM

I read somewhere you need to drop temp to 0.1 on gemma for tools.

Not sure why (too amateur sorry).

Though I think qwen was natively trained on toolcalling.