| # lllqaq/R2EGym-7B-Agent-Coder-Instruct-filtered1 | |
| This model is a full SFT fine-tune of `Qwen/Qwen2.5-Coder-7B-Instruct` on traj_gpt5mini (filtered1). | |
| Export source checkpoint: `/data/jiarong/LLaMA-Factory/saves/R2EGym-7B-Agent-Coder-Instruct1/checkpoint-442` | |