Collection of models and datasets for Beyond Binary Rewards: Training LMs to Reason about their Uncertainty
Mehul Damani
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
updated a dataset 4 days ago
mehuldamani/math-team-composites published a dataset 4 days ago
mehuldamani/math-team-composites updated a dataset 29 days ago
mehuldamani/marl-lib-repair-n4r3-inf1Organizations
None yet
models 290
mehuldamani/bugfixing-new-arl-add
Text Generation • 8B • Updated • 7
mehuldamani/countdown-arl-sft-add-v8
Text Generation • 3B • Updated • 5
mehuldamani/rlvr-v6-high-corrupt-high-kl
Text Generation • 3B • Updated • 6
mehuldamani/rlvr-v6-high-corrupt-kl
Text Generation • 3B • Updated • 8
mehuldamani/story-llm-as-judge-binarized-v2-highkl
Text Generation • 8B • Updated • 15
mehuldamani/story-llm-as-judge-binarized-v2-nokl
Text Generation • 8B • Updated • 12
mehuldamani/story-full-disc-judge-binarized-v2-nolr
Text Generation • 8B • Updated • 8
mehuldamani/story-full-disc-judge-binarized-feature-v4-new
Text Generation • 8B • Updated • 7
mehuldamani/story-full-disc-judge-binarized-feature-v5-new
Text Generation • 8B • Updated • 6
mehuldamani/countdown_arl-sft-no-combine-v2
Text Generation • 3B • Updated • 8
datasets 94
mehuldamani/math-team-composites
Viewer • Updated • 21k • 43
mehuldamani/marl-lib-repair-n4r3-inf1
Viewer • Updated • 6.66k • 64
mehuldamani/arxiv_KL_story_v1_features
Viewer • Updated • 200 • 4
mehuldamani/arxiv_feature_space_v1-story-features-sample-v1
Viewer • Updated • 200 • 14
mehuldamani/neurips-story-main-story-features-sample-v1
Viewer • Updated • 200 • 14
mehuldamani/neurips-story-main
Viewer • Updated • 500 • 17
mehuldamani/neurips-story-test-v8-story-features-sample-v2
Viewer • Updated • 100 • 7
mehuldamani/neurips-story-test-v8-story-features-sample-v1
Viewer • Updated • 50 • 15
mehuldamani/neurips-story-test-v7-story-features-sample-v1
Viewer • Updated • 50 • 5
mehuldamani/neurips-story-test-v6-story-features-sample-v5
Viewer • Updated • 20 • 8