qwen2.5-7b_solver_iter1

• Model alias: qwen2.5-7b
• Base model: Qwen2.5-7B-Instruct
• Version: v1.9.21
• Solver iteration: 1
• Global step: 20
• Source experiment: long_solver_v1.9.21_iter1_grpo_group8_qwen2.5-7b-instruct
• Source local HF checkpoint: checkpoints/dr-zero/long_solver_v1.9.21_iter1_grpo_group8_qwen2.5-7b-instruct/merged_hf_actor_gs20
• Collection: https://huggingface.co/collections/wckwan/scope