Ctrl+K
- Qwen3-4B-Thinking-REINFORCE-Gridlink-policy
- Qwen3-4B-Thinking-grpo-3tasks-policy1000
- Qwen3-4B-Thinking-grpo-har-Gridlink-policy820
- Qwen3-4B-Thinking-har-3task-policy500
- Qwen3-4B-thinking-grpo_epshigh0-5_gridlink_no_personality_policy320
- Qwen3-4B-thinking-grpo_epshigh0-5_gridlink_vs_qwen34Bthinking_policy240
- Qwen3-4B-thinking_sft_agent2_grpo_1e-6_epshigh0-5_3task_policy620
- Qwen3-4B-thinking_sft_har_agent2_grpo_1e-6_epshigh0-5_3task_policy620
- Qwen3-4B-thinking_sft_har_agent2_grpo_1e-6_epshigh0-5_3task_vs_qwen34bthinking_policy500
- Qwen3-4B-thinking_sft_har_agent2_grpo_1e-6_epshigh0-5_gridlink_vs_qwen4bthink_policy340
- Qwen3-4b-thinking_sft_har_agent2_grpo_1e-6_epshigh0-5_gridlink_policy800
- Qwen3-4b-thinking_sft_har_agent2_grpo_1e-6_epshigh0-5_gridlink_policy920
- 1.56 kB
- 91 Bytes