·
AI & ML interests
NLP, RL
Organizations
Viewer
• Updated • 12.5k • 38
Viewer
• Updated • 361k • 12
Dahoas/aimo-validation-aime
Viewer
• Updated • 90 • 9
Dahoas/qwen-1.5-4B-default-positives-epoch-1-100
Viewer
• Updated • 290k • 31
Dahoas/qwen-1.5-4B-tree-positives-epoch-2-100
Viewer
• Updated • 491k • 14
Dahoas/qwen-1.5-4B-tree-positives-epoch-1-100
Viewer
• Updated • 477k • 12
Dahoas/qwen-1.5-4B-epoch-1-test-100
Viewer
• Updated • 498k • 12
Dahoas/qwen-1.5-4B-K-100-test
Viewer
• Updated • 500k • 16
Dahoas/MATH_train_K_100_qwen_1.5_4B_outputs
Viewer
• Updated • 750k • 11
Viewer
• Updated • 750k • 23
• 2
Viewer
• Updated • 8.79k • 5
Dahoas/MATH_full_chat_format
Viewer
• Updated • 12.5k • 5
• 1
Viewer
• Updated • 7.91k • 8
Viewer
• Updated • 4.01k • 6
Viewer
• Updated • 1k • 16
• 1
Viewer
• Updated • 1k • 139
Dahoas/prompted_hf_cot_gsm8k
Viewer
• Updated • 8.79k • 10
• 7
Viewer
• Updated • 8.79k • 5
• 1
Dahoas/cot_gsm8k_three_step
Viewer
• Updated • 741 • 16
Dahoas/no_nl_cot_gsm8k_three_step
Viewer
• Updated • 2.09k • 12
Dahoas/no_nl_cot_gsm8k_toy
Viewer
• Updated • 2.42k • 21
Viewer
• Updated • 578 • 5
Viewer
• Updated • 32.2k • 17
Dahoas/split_no_nl_cot_gsm8k
Viewer
• Updated • 28k • 68
• 1
Viewer
• Updated • 8.68k • 33
• 2
Dahoas/gsm_socratic_conditional
Viewer
• Updated • 52.4k • 13
• 1
Dahoas/cot_gsm8k_socratic
Viewer
• Updated • 8.79k • 57
• 4
Viewer
• Updated • 8.79k • 180
• 6
Viewer
• Updated • 20k • 31
• 4
Viewer
• Updated • 207k • 46
• 3