·
AI & ML interests
NLP, RL
Organizations
Viewer
• Updated • 12.5k • 20
Viewer
• Updated • 361k • 19
Dahoas/aimo-validation-aime
Viewer
• Updated • 90 • 41
Dahoas/qwen-1.5-4B-default-positives-epoch-1-100
Viewer
• Updated • 290k • 13
Dahoas/qwen-1.5-4B-tree-positives-epoch-2-100
Viewer
• Updated • 491k • 15
Dahoas/qwen-1.5-4B-tree-positives-epoch-1-100
Viewer
• Updated • 477k • 59
Dahoas/qwen-1.5-4B-epoch-1-test-100
Viewer
• Updated • 498k • 16
Dahoas/qwen-1.5-4B-K-100-test
Viewer
• Updated • 500k • 22
Dahoas/MATH_train_K_100_qwen_1.5_4B_outputs
Viewer
• Updated • 750k • 17
Viewer
• Updated • 750k • 23
• 2
Viewer
• Updated • 8.79k • 31
Dahoas/MATH_full_chat_format
Viewer
• Updated • 12.5k • 38
• 1
Viewer
• Updated • 7.91k • 57
Viewer
• Updated • 4.01k • 19
Viewer
• Updated • 1k • 29
• 1
Viewer
• Updated • 1k • 307
Dahoas/prompted_hf_cot_gsm8k
Viewer
• Updated • 8.79k • 45
• 7
Viewer
• Updated • 8.79k • 14
• 1
Dahoas/cot_gsm8k_three_step
Viewer
• Updated • 741 • 22
Dahoas/no_nl_cot_gsm8k_three_step
Viewer
• Updated • 2.09k • 37
Dahoas/no_nl_cot_gsm8k_toy
Viewer
• Updated • 2.42k • 47
Viewer
• Updated • 578 • 30
Viewer
• Updated • 32.2k • 60
Dahoas/split_no_nl_cot_gsm8k
Viewer
• Updated • 28k • 16
• 1
Viewer
• Updated • 8.68k • 41
• 2
Dahoas/gsm_socratic_conditional
Viewer
• Updated • 52.4k • 31
• 1
Dahoas/cot_gsm8k_socratic
Viewer
• Updated • 8.79k • 73
• 4
Viewer
• Updated • 8.79k • 150
• 7
Viewer
• Updated • 20k • 8
• 4
Viewer
• Updated • 207k • 33
• 3