·
AI & ML interests
NLP, RL
Organizations
Viewer
• Updated • 12.5k • 17
Viewer
• Updated • 361k • 9
Dahoas/aimo-validation-aime
Viewer
• Updated • 90 • 10
Dahoas/qwen-1.5-4B-default-positives-epoch-1-100
Viewer
• Updated • 290k • 10
Dahoas/qwen-1.5-4B-tree-positives-epoch-2-100
Viewer
• Updated • 491k • 5
Dahoas/qwen-1.5-4B-tree-positives-epoch-1-100
Viewer
• Updated • 477k • 8
Dahoas/qwen-1.5-4B-epoch-1-test-100
Viewer
• Updated • 498k • 4
Dahoas/qwen-1.5-4B-K-100-test
Viewer
• Updated • 500k • 38
Dahoas/MATH_train_K_100_qwen_1.5_4B_outputs
Viewer
• Updated • 750k • 21
Viewer
• Updated • 750k • 15
• 2
Viewer
• Updated • 8.79k • 7
Dahoas/MATH_full_chat_format
Viewer
• Updated • 12.5k • 3
• 1
Viewer
• Updated • 7.91k • 4
Viewer
• Updated • 4.01k • 15
Viewer
• Updated • 1k • 12
• 1
Viewer
• Updated • 1k • 121
Dahoas/prompted_hf_cot_gsm8k
Viewer
• Updated • 8.79k • 11
• 7
Viewer
• Updated • 8.79k • 10
• 1
Dahoas/cot_gsm8k_three_step
Viewer
• Updated • 741 • 11
Dahoas/no_nl_cot_gsm8k_three_step
Viewer
• Updated • 2.09k • 20
Dahoas/no_nl_cot_gsm8k_toy
Viewer
• Updated • 2.42k • 66
Viewer
• Updated • 578 • 12
Viewer
• Updated • 32.2k • 12
Dahoas/split_no_nl_cot_gsm8k
Viewer
• Updated • 28k • 11
• 1
Viewer
• Updated • 8.68k • 11
• 2
Dahoas/gsm_socratic_conditional
Viewer
• Updated • 52.4k • 9
• 1
Dahoas/cot_gsm8k_socratic
Viewer
• Updated • 8.79k • 13
• 4
Viewer
• Updated • 8.79k • 174
• 6
Viewer
• Updated • 20k • 11
• 4
Viewer
• Updated • 207k • 24
• 3