dogtooth/reasoning_state_rl
Viewer • Updated • 262k • 10
Tianjian Li
dogtooth
AI & ML interests
None yet
Organizations
dogtooth/rc-annotated-sft
Viewer • Updated • 1.49k • 40
dogtooth/polaris_filtered_removed_all_correct
Viewer • Updated • 38.1k • 25
dogtooth/polaris_filtered_less_than_half_correct
Viewer • Updated • 13.8k • 26
dogtooth/llm_tool_self_context_management_sft
Viewer • Updated • 12.4k • 33
dogtooth/tool_call_truncated_synthesized_traj
Viewer • Updated • 4.54k • 18
dogtooth/tool_verify_truncated
Viewer • Updated • 2.85k • 9
dogtooth/math_training_24k
Viewer • Updated • 23.9k • 10
dogtooth/Big-Math-RL-Verified
Viewer • Updated • 1.52M • 122
dogtooth/default_project_dev_test
Viewer • Updated • 4k • 19
dogtooth/Big-Math-Selected-500
Viewer • Updated • 3.5k • 21
dogtooth/Big-Math-RL-Verified-Chinese
Viewer • Updated • 251k • 194
dogtooth/mmlu
Viewer • Updated • 14.2k • 86
dogtooth/boolq
Viewer • Updated • 3.27k • 12
dogtooth/gpqa
Viewer • Updated • 448 • 31
dogtooth/math_qa
Viewer • Updated • 2.99k • 13
dogtooth/wiqa
Viewer • Updated • 3k • 28 • 1
dogtooth/pubmed_qa
Viewer • Updated • 500 • 15
dogtooth/strategyqa
Viewer • Updated • 687 • 32
dogtooth/aqua_rat
Viewer • Updated • 254 • 32
dogtooth/quartz
Viewer • Updated • 784 • 14
dogtooth/sciq
Viewer • Updated • 1k • 16
dogtooth/art
Viewer • Updated • 1.53k • 13
dogtooth/winogrande
Viewer • Updated • 1.27k • 15
dogtooth/truthful_qa
Viewer • Updated • 817 • 16
dogtooth/social_i_qa
Viewer • Updated • 1.95k • 29
dogtooth/piqa
Viewer • Updated • 1.84k • 18
dogtooth/logiqa
Viewer • Updated • 651 • 52
dogtooth/commonsense_qa
Viewer • Updated • 1.22k • 15
dogtooth/copa
Viewer • Updated • 100 • 30