Collection of models and datasets for Beyond Binary Rewards: Training LMs to Reason about their Uncertainty
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
updated a model about 19 hours ago
mehuldamani/bug_fixing_new-arl-add_multiply published a model about 19 hours ago
mehuldamani/bug_fixing_new-arl-add_multiply updated a model about 19 hours ago
mehuldamani/bug_fixing_rlvr-7b-nokl-v2Organizations
None yet
models 263
mehuldamani/bug_fixing_new-arl-add_multiply
Text Generation • 8B • Updated • 97
mehuldamani/bug_fixing_rlvr-7b-nokl-v2
Text Generation • 8B • Updated • 73
mehuldamani/olmo-sft-v1
Text Generation • 7B • Updated • 106
mehuldamani/countdown_arl-sft-add_multiply-v8
Text Generation • 3B • Updated • 216
mehuldamani/countdown_arl-sft-multiply-v8
Text Generation • 3B • Updated • 223
mehuldamani/countdown_rlvr-v6-high-corrupt
Text Generation • 3B • Updated • 231
mehuldamani/countdown_rlvr-v6-high-corrupt-gold
Text Generation • 3B • Updated • 225
mehuldamani/bug_fixing_sft-v1
Text Generation • 8B • Updated • 265
mehuldamani/code_gen_arl-ast-addmultiply-7b-v1
Text Generation • 8B • Updated • 337
mehuldamani/code_gen_rlvr-ast-7b-v2
Text Generation • 8B • Updated • 249
datasets 69
mehuldamani/countdown_code_10_corrupted
Viewer • Updated • 15.6k • 42
mehuldamani/mini-story
Viewer • Updated • 1.1k • 10
mehuldamani/story-classifier-Instruct-SFT-v1
Viewer • Updated • 22k • 10
mehuldamani/story-classifier-Instruct-v1
Viewer • Updated • 22k • 6
mehuldamani/story-tranch-2
Viewer • Updated • 26k • 11
mehuldamani/story-tranch-1
Viewer • Updated • 26k • 10
mehuldamani/LitBench-tranch-4
Viewer • Updated • 11.7k • 3
mehuldamani/LitBench-tranch-3
Viewer • Updated • 11.7k • 6
mehuldamani/LitBench-tranch-2
Viewer • Updated • 11.7k • 1
mehuldamani/LitBench-tranch-1
Viewer • Updated • 11.7k • 8