JoanneJegou

GRPO_qwen_merge

JoanneJegou/GRPO_qwen_merge

GRPO_qwen_merge is a machine learning model from JoanneJegou. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

GRPO on math model using Multilingual and General Knowledge data. Checkpoint 1000 was merged back with base model Qwen3-1.7 to recover lost capabilities while improving format alignment.