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
13 days ago
mehuldamani/synthtool-v1-modified
published
a dataset
13 days ago
mehuldamani/synthtool-v1-modified
updated
a dataset
21 days ago
mehuldamani/grok-4-trial
Organizations
None yet
models
9
mehuldamani/big-math-digits-v2-brier
8B
•
Updated
•
44
mehuldamani/hotpot-v2-correctness-7b
Text Generation
•
8B
•
Updated
•
64
mehuldamani/orm-big-math-digits-v2-correctness
Text Classification
•
7B
•
Updated
•
33
mehuldamani/big-math-digits-v2-brier-base-tabc
Text Generation
•
8B
•
Updated
•
142
mehuldamani/big-math-digits-v2-correctness
Text Generation
•
8B
•
Updated
•
60
mehuldamani/orm-big-math-digits-v1-correctness
Text Classification
•
7B
•
Updated
•
2
mehuldamani/qwen-base-verifier-sft-v1
Text Generation
•
8B
•
Updated
•
29
mehuldamani/orm-hotpot-v2-final-correctness
Text Classification
•
7B
•
Updated
•
39
mehuldamani/hotpot-v2-brier-7b-no-split
Text Generation
•
8B
•
Updated
•
96
datasets
9
mehuldamani/synthtool-v1-modified
Viewer
•
Updated
•
10k
•
98
mehuldamani/grok-4-trial
Viewer
•
Updated
•
20
•
83
mehuldamani/r1-trial
Viewer
•
Updated
•
20
•
79
mehuldamani/or-trial
Viewer
•
Updated
•
2
•
80
mehuldamani/gpt-5-trialv3
Viewer
•
Updated
•
5
•
94
mehuldamani/gpt-5-trialv2
Viewer
•
Updated
•
5
•
87
mehuldamani/gpt5-trial
Viewer
•
Updated
•
1
•
91
mehuldamani/big-math-digits
Viewer
•
Updated
•
31k
•
68
mehuldamani/hotpot_qa
Viewer
•
Updated
•
20.5k
•
270