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
published
a model
about 16 hours ago
mehuldamani/regularBrier_mixedNumCandidates_rlcr_multi_from_rlvr_chkpt360
published
a model
2 days ago
mehuldamani/strongBrier_newPrompt_rlcr_multi_from_rlvr_chkpt360
published
a model
3 days ago
mehuldamani/rlcr_single_from_rlvr_chkpt360
Organizations
None yet
models
210
mehuldamani/regularBrier_mixedNumCandidates_rlcr_multi_from_rlvr_chkpt360
Updated
mehuldamani/strongBrier_newPrompt_rlcr_multi_from_rlvr_chkpt360
Updated
mehuldamani/rlcr_multi_from_rlvr_chkpt360
Updated
mehuldamani/rlcr_single_from_rlvr_chkpt360
Updated
mehuldamani/rerun_rlcr_single_from_rlvr_chkpt480
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi_k_5
Updated
mehuldamani/math_rlcr_single_try1_cl4096
Updated
mehuldamani/math_rlvr_single_try1_cl4096
Updated
mehuldamani/math_rlvr_multi_try1_cl4096
Updated
mehuldamani/math_rlcr_multi_try1_cl4096
Updated
datasets
54
mehuldamani/hotpot_qa_test_gold_removed_1
Viewer
•
Updated
•
20.5k
•
9
mehuldamani/hotpot_qa_test_gold_removed_2
Viewer
•
Updated
•
20.5k
•
8
mehuldamani/hotpot_qa_trainTest_gold_removed_2
Viewer
•
Updated
•
20.5k
•
20
mehuldamani/hotpot2Removed_eval_10Runs_rlvr_multi_on_rlcr_multi
Viewer
•
Updated
•
500
•
16
mehuldamani/big-math-tough
Viewer
•
Updated
•
18.5k
•
66
mehuldamani/medTroubleshootig-rlvr-220-evaled-on-rlcr
Viewer
•
Updated
•
5k
•
13
mehuldamani/medTroubleshootig-rlvr-220-evaled-on-rlvr
Viewer
•
Updated
•
5k
•
13
mehuldamani/medDataset_25k
Viewer
•
Updated
•
75k
•
353
mehuldamani/medDataset
Viewer
•
Updated
•
1.29M
•
32
mehuldamani/qwen3_8b_ambigQA_rlcr_multi_analysis
Viewer
•
Updated
•
2k
•
3