prefixsliding/qwen3_sft_correct_saving_v6
Viewer
• Updated • 659 • 15
prefixsliding/train_v6_sub
Viewer
• Updated • 436k • 38
prefixsliding/qwen3_sft_correct_saving_v5
Viewer
• Updated • 564 • 10
prefixsliding/train_v6-filtered
Viewer
• Updated • 52k • 14
prefixsliding/train_v6_qwen
Viewer
• Updated • 436k • 12
Viewer
• Updated • 34.6k • 45
Updated • 20
prefixsliding/Qwen3-1.7B-0608
Viewer
• Updated • 148k • 183
prefixsliding/train_ds_v5-qwen3-missing
Viewer
• Updated • 223k • 7
prefixsliding/Qwen3-1.7B-0607
Viewer
• Updated • 148k • 193
prefixsliding/qwen3_output_parallel_tool_exec
Viewer
• Updated • 21 • 15
prefixsliding/qwen3_sft_correct_saving_v4
Viewer
• Updated • 562 • 10
prefixsliding/qwen3_sft_correct_saving_v3
Viewer
• Updated • 559 • 11
prefixsliding/train_ds_v5-missing-difficulty
Viewer
• Updated • 509k • 6
prefixsliding/train_v5-filtered
Viewer
• Updated • 212k • 9
Viewer
• Updated • 599k • 5
prefixsliding/qwen3_sft_correct_v2
Viewer
• Updated • 547 • 9
prefixsliding/qwen3_1.7B_sft_correct_v1_viewer
Viewer
• Updated • 30 • 12
prefixsliding/DeepSeek-R1-Distill-Qwen-1.5-difficulty
Viewer
• Updated • 189k • 25
prefixsliding/verify_sft_masking
Viewer
• Updated • 1 • 8
prefixsliding/qwen3_sft_correct_v1
Viewer
• Updated • 437 • 10
prefixsliding/deepseek-r1-to-qwen3_5_17
Viewer
• Updated • 747 • 13
prefixsliding/verify_rl_masking
Viewer
• Updated • 6 • 9
prefixsliding/verify_saving_reward
Viewer
• Updated • 6 • 9
prefixsliding/qwen3_output_new
Viewer
• Updated • 2 • 10
prefixsliding/qwen3_output_viewer
Viewer
• Updated • 9 • 12
prefixsliding/deepseek_output_viewer
Viewer
• Updated • 30 • 7
Viewer
• Updated • 599k • 13
Viewer
• Updated • 599k • 7
Viewer
• Updated • 599k • 10