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 1 day ago
mehuldamani/code_gen_arl-ast-addmultiply-7b-v1 published a model 1 day ago
mehuldamani/code_gen_arl-ast-addmultiply-7b-v1 updated a model 1 day ago
mehuldamani/code_gen_rlvr-ast-7b-v2Organizations
None yet
models 255
mehuldamani/code_gen_arl-ast-addmultiply-7b-v1
Text Generation • 8B • Updated • 302
mehuldamani/code_gen_rlvr-ast-7b-v2
Text Generation • 8B • Updated • 222
mehuldamani/bug_fixing_arl-7b-addmultiply-v4
Text Generation • 8B • Updated • 221
mehuldamani/bug_fixing_rlvr-7b-v4
Text Generation • 8B • Updated • 232
mehuldamani/sft-corrupted-qwen-v3
Text Generation • 3B • Updated • 626
mehuldamani/sft-corrupted-qwen-v2
Text Generation • 3B • Updated • 370
mehuldamani/sft-corrupted-qwen-v1
Text Generation • 3B • Updated • 533
mehuldamani/rlvr-qwen-hmaze-v1
Text Generation • 3B • Updated • 307
mehuldamani/rlm-qwen-hmaze-v1-high-fifo
Text Generation • 3B • Updated • 299
mehuldamani/hmaze-oracle-v1-multiply
Text Generation • 3B • Updated • 284
datasets 69
mehuldamani/countdown_code_10_corrupted
Viewer • Updated • 15.6k • 40
mehuldamani/mini-story
Viewer • Updated • 1.1k • 11
mehuldamani/story-classifier-Instruct-SFT-v1
Viewer • Updated • 22k • 11
mehuldamani/story-classifier-Instruct-v1
Viewer • Updated • 22k • 10
mehuldamani/story-tranch-2
Viewer • Updated • 26k • 13
mehuldamani/story-tranch-1
Viewer • Updated • 26k • 14
mehuldamani/LitBench-tranch-4
Viewer • Updated • 11.7k • 10
mehuldamani/LitBench-tranch-3
Viewer • Updated • 11.7k • 8
mehuldamani/LitBench-tranch-2
Viewer • Updated • 11.7k • 6
mehuldamani/LitBench-tranch-1
Viewer • Updated • 11.7k • 9