AI & ML interests
None defined yet.
Viewer
• Updated
• 39.3k • 7
Viewer
• Updated
• 20.5k • 7
dsrselfcorr/qwen25_star_baseline_sft_c2r
Viewer
• Updated
• 18.8k • 7
dsrselfcorr/qwen25_star_baseline_sft_w2c_3
Viewer
• Updated
• 4.33k • 6
dsrselfcorr/qwen25_star_baseline_sft_w2c_2
Viewer
• Updated
• 6.07k • 7
dsrselfcorr/qwen25_star_baseline_sft_w2c
Viewer
• Updated
• 10.1k • 5
dsrselfcorr/qwen25_star_baseline_gen1
Viewer
• Updated
• 48.6k • 6
dsrselfcorr/qwen25_star_baseline_gen2
Viewer
• Updated
• 39.4k • 6
dsrselfcorr/star_turn2_prompt2
Viewer
• Updated
• 48.6k • 5
dsrselfcorr/star_turn2_prompt
Viewer
• Updated
• 45k • 5
dsrselfcorr/warmup_sft_merged_clean
Viewer
• Updated
• 32k • 6
dsrselfcorr/warmup_sft_merged2_clean
Viewer
• Updated
• 32k • 6
Viewer
• Updated
• 416k • 7
dsrselfcorr/warmup_sft_merged2
Viewer
• Updated
• 32k • 6
dsrselfcorr/math_test_prompt
Viewer
• Updated
• 500 • 6
dsrselfcorr/warmup_sft_merged
Viewer
• Updated
• 32k • 6
dsrselfcorr/turn3_verify_true_sft_processed
Viewer
• Updated
• 15.7k • 7
dsrselfcorr/turn3_verify_true_sft
Viewer
• Updated
• 15.7k • 6
dsrselfcorr/turn3_verify_wrong_and_correct_sft_processed
Viewer
• Updated
• 16.3k • 5
dsrselfcorr/turn3_verify_wrong_and_correct_sft
Viewer
• Updated
• 16.3k • 4
dsrselfcorr/self_corr_first_wrong_qwenbase_prompt2_gen1
Viewer
• Updated
• 6.47k • 6
dsrselfcorr/self_corr_first_wrong_qwenbase_prompt2_gen2
Viewer
• Updated
• 6.47k • 6
dsrselfcorr/self_corr_first_wrong_qwenbase_prompt1_gen2
Viewer
• Updated
• 1.75k • 7
dsrselfcorr/self_corr_first_wrong_qwenbase_prompt1_gen1
Viewer
• Updated
• 1.75k • 6
dsrselfcorr/corr_iter2_prompt_wrong_initial
Viewer
• Updated
• 1.76k • 6
dsrselfcorr/corr_iter2_prompt_wrong_initial2
Viewer
• Updated
• 6.47k • 6
dsrselfcorr/corr_sft_collection_verify_true
Viewer
• Updated
• 15.7k • 5
dsrselfcorr/corr_sft_turn3_prompt
Viewer
• Updated
• 1.76k • 6
dsrselfcorr/corr_iter2_prompt
Viewer
• Updated
• 45k • 4
dsrselfcorr/corr_iter1_gen_with_rewards
Viewer
• Updated
• 40k • 6