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
5 days ago
mehuldamani/abstain-v3
updated
a model
7 days ago
mehuldamani/RLVR-hotpot-olmo-v3
updated
a model
7 days ago
mehuldamani/RLCR-hotpot-olmo-v3
Organizations
None yet
models
135
mehuldamani/abstain-v3
Text Generation
•
8B
•
Updated
•
34
mehuldamani/RLVR-hotpot-olmo-v3
Text Generation
•
7B
•
Updated
•
24
mehuldamani/RLCR-hotpot-olmo-v3
Text Generation
•
7B
•
Updated
•
22
mehuldamani/calibration-only-v5
Updated
mehuldamani/abstain-v2
Text Generation
•
8B
•
Updated
•
3
mehuldamani/RLVR-hotpot-olmo-v2
Updated
mehuldamani/abstain-v1
Text Generation
•
8B
•
Updated
•
27
•
1
mehuldamani/RLCR-hotpot-octo
Text Generation
•
8B
•
Updated
•
9
•
1
mehuldamani/RLVR-hotpot-octo
Text Generation
•
8B
•
Updated
•
17
mehuldamani/RLCR-hotpot-olmo-v2
Text Generation
•
7B
•
Updated
•
25
datasets
23
mehuldamani/half_hotpot_qa
Viewer
•
Updated
•
10.3k
•
19
mehuldamani/math_single_models_pass_k_evals_onMath_nov13
Viewer
•
Updated
•
500
•
8
mehuldamani/math_multi_models_pass_k_evals_onMath_nov13
Viewer
•
Updated
•
500
•
8
mehuldamani/hotpot_qa_single_models_pass_k_evals_onHotpot_nov11
Viewer
•
Updated
•
500
•
25
mehuldamani/hotpot_qa_multi_models_pass_k_evals_onHotpot_nov11
Viewer
•
Updated
•
500
•
22
mehuldamani/hotpot_qa_for_multi
Viewer
•
Updated
•
20.5k
•
45
mehuldamani/intent-trial
Viewer
•
Updated
•
20
•
36
mehuldamani/judge-v1-step600
Viewer
•
Updated
•
30
•
25
mehuldamani/judge-v1-base
Viewer
•
Updated
•
30
•
33
mehuldamani/judge-step600
Viewer
•
Updated
•
10
•
28