Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
ReleaseHugging Face
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
September 3, 20261 min readPublished byHugging Face
Tags
fine-tuning