Fine-tune Google's Gemma 3

Re:Fine-tune Google's Gemma 3 by arkmm on Wednesday March 19, 2025 @05:01PM (#43417290)

There are some options out there, depending on what type of task you're trying to fine tune. I think RL finetuning for DeepSeek e.g. isn't well developed yet, but you can finetune a small LLama model (~3B params) for classification or extraction tasks and it works really well. What sort of tasks were you looking at finetuning for?

[ Parent | on HN ]

Re:Fine-tune Google's Gemma 3 by nwienert on Wednesday March 19, 2025 @05:40PM (#43417606)

Code generation or question answering. But ideally 70+B

[ Parent | on HN ]