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 dataset
about 17 hours ago
mehuldamani/judge-new-sft
published
a dataset
about 17 hours ago
mehuldamani/judge-new-sft
updated
a dataset
about 17 hours ago
mehuldamani/judge-new-base
Organizations
None yet
models
137
mehuldamani/classifier-v3-Base-global-step-156
Text Classification
•
8B
•
Updated
•
11
mehuldamani/classifier-v3-SFT-global-step-156
Text Classification
•
8B
•
Updated
•
10
mehuldamani/abstain-v3
Text Generation
•
8B
•
Updated
•
39
mehuldamani/RLVR-hotpot-olmo-v3
Text Generation
•
7B
•
Updated
•
27
mehuldamani/RLCR-hotpot-olmo-v3
Text Generation
•
7B
•
Updated
•
24
mehuldamani/calibration-only-v5
Updated
mehuldamani/abstain-v2
Text Generation
•
8B
•
Updated
•
7
mehuldamani/RLVR-hotpot-olmo-v2
Updated
mehuldamani/abstain-v1
Text Generation
•
8B
•
Updated
•
30
•
1
mehuldamani/RLCR-hotpot-octo
Text Generation
•
8B
•
Updated
•
14
•
1
datasets
35
mehuldamani/judge-new-sft
Viewer
•
Updated
•
50
mehuldamani/judge-new-base
Viewer
•
Updated
•
50
mehuldamani/wildchat-tranch-4
Viewer
•
Updated
•
61.4k
mehuldamani/wildchat-tranch-3
Viewer
•
Updated
•
61.4k
mehuldamani/wildchat-tranch-2
Viewer
•
Updated
•
61.4k
mehuldamani/wildchat-tranch-1
Viewer
•
Updated
•
60.9k
mehuldamani/classifier-v1-SFT
Viewer
•
Updated
•
21k
•
13
mehuldamani/classifier-v1-Base
Viewer
•
Updated
•
21k
•
14
mehuldamani/classifier-first-run
Viewer
•
Updated
•
400
•
8
mehuldamani/trials-nov-v6-classifier-v2
Viewer
•
Updated
•
100
•
4