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 18 hours ago
mehuldamani/sft-corrupted-qwen-v3 published a model about 18 hours ago
mehuldamani/sft-corrupted-qwen-v3 updated a dataset about 21 hours ago
mehuldamani/countdown_code_10_corruptedOrganizations
None yet
models 251
mehuldamani/sft-corrupted-qwen-v3
Text Generation • 3B • Updated • 293
mehuldamani/sft-corrupted-qwen-v2
Text Generation • 3B • Updated • 346
mehuldamani/sft-corrupted-qwen-v1
Text Generation • 3B • Updated • 480
mehuldamani/rlvr-qwen-hmaze-v1
Text Generation • 3B • Updated • 280
mehuldamani/rlm-qwen-hmaze-v1-high-fifo
Text Generation • 3B • Updated • 272
mehuldamani/hmaze-oracle-v1-multiply
Text Generation • 3B • Updated • 259
mehuldamani/hmaze-oracle-v1
Text Generation • 3B • Updated • 260
mehuldamani/sft-qwen-hmaze-v2
Text Generation • 3B • Updated • 684
mehuldamani/sft-qwen-hmaze-v1
Text Generation • 3B • Updated • 382
mehuldamani/sft-qwen-zmaze-v3
Text Generation • 3B • Updated • 184
datasets 69
mehuldamani/countdown_code_10_corrupted
Updated • 8
mehuldamani/mini-story
Viewer • Updated • 1.1k • 19
mehuldamani/story-classifier-Instruct-SFT-v1
Viewer • Updated • 22k • 16
mehuldamani/story-classifier-Instruct-v1
Viewer • Updated • 22k • 15
mehuldamani/story-tranch-2
Viewer • Updated • 26k • 28
mehuldamani/story-tranch-1
Viewer • Updated • 26k • 45
mehuldamani/LitBench-tranch-4
Viewer • Updated • 11.7k • 16
mehuldamani/LitBench-tranch-3
Viewer • Updated • 11.7k • 15
mehuldamani/LitBench-tranch-2
Viewer • Updated • 11.7k • 14
mehuldamani/LitBench-tranch-1
Viewer • Updated • 11.7k • 16