Fine-Tuning Gemma 4 for Function Calling with TRL's New Multimodal Tool Support
pulkitgovrani
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Gemma 4 ships with native function calling built in — trained from scratch, not prompt-engineered. But "built in" and "tuned for your specific tools" are different things. If you have a set of internal APIs, a specific tool schema, or edge-case behaviors that the base model handles inconsistently, fine-tuning on your own function-calling data is the right move. TRL (Transformer Reinforcement Learning library) added multimodal to