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
1 day ago
mehuldamani/classifier-v1-Base
published
a dataset
1 day ago
mehuldamani/classifier-v1-Base
updated
a dataset
1 day ago
mehuldamani/classifier-v1-SFT
Organizations
None yet
models
135
mehuldamani/abstain-v3
Text Generation
•
8B
•
Updated
•
37
mehuldamani/RLVR-hotpot-olmo-v3
Text Generation
•
7B
•
Updated
•
26
mehuldamani/RLCR-hotpot-olmo-v3
Text Generation
•
7B
•
Updated
•
23
mehuldamani/calibration-only-v5
Updated
mehuldamani/abstain-v2
Text Generation
•
8B
•
Updated
•
5
mehuldamani/RLVR-hotpot-olmo-v2
Updated
mehuldamani/abstain-v1
Text Generation
•
8B
•
Updated
•
29
•
1
mehuldamani/RLCR-hotpot-octo
Text Generation
•
8B
•
Updated
•
12
•
1
mehuldamani/RLVR-hotpot-octo
Text Generation
•
8B
•
Updated
•
18
mehuldamani/RLCR-hotpot-olmo-v2
Text Generation
•
7B
•
Updated
•
27
datasets
29
mehuldamani/classifier-v1-Base
Viewer
•
Updated
•
21k
•
7
mehuldamani/classifier-v1-SFT
Viewer
•
Updated
•
21k
•
5
mehuldamani/classifier-first-run
Viewer
•
Updated
•
400
•
7
mehuldamani/trials-nov-v6-classifier-v2
Viewer
•
Updated
•
100
•
3
mehuldamani/trials-nov-v6-classifier
Viewer
•
Updated
•
50
•
5
mehuldamani/ambigQA
Viewer
•
Updated
•
12k
•
5
mehuldamani/half_hotpot_qa
Viewer
•
Updated
•
10.3k
•
28
mehuldamani/math_single_models_pass_k_evals_onMath_nov13
Viewer
•
Updated
•
500
•
14
mehuldamani/math_multi_models_pass_k_evals_onMath_nov13
Viewer
•
Updated
•
500
•
13
mehuldamani/hotpot_qa_single_models_pass_k_evals_onHotpot_nov11
Viewer
•
Updated
•
500
•
32