Revision history
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps — 1 version recorded. Nothing here has been overwritten.
-
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
From the publisher, with its history intact.
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps — 1 version recorded. Nothing here has been overwritten.