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
1 day ago
mehuldamani/qwen3_8b_medical_rlvr_multi
published
a model
3 days ago
mehuldamani/qwen3_8b_medical_rlcr_single_judgeYesPartialCredit
published
a model
3 days ago
mehuldamani/qwen3_8b_medical_rlcr_single_judgeNoPartialCredit
Organizations
None yet
models
156
mehuldamani/qwen3_8b_medical_rlvr_multi
Updated
mehuldamani/qwen3_8b_medical_rlcr_single_judgeYesPartialCredit
Updated
mehuldamani/qwen3_8b_medical_rlcr_single_judgeNoPartialCredit
Updated
mehuldamani/qwen3_8b_medical_rlcr_single_reStarting
Updated
mehuldamani/qwen3_8b_medical_rlcr_single_withJudge_noPartialCredit
Updated
mehuldamani/qwen3_8b_medical_rlvr_single
Updated
mehuldamani/qwen3_8b_medical_rlcr_single
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple
Updated
mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_newAccReward_standardPrompt_initFromFirstModel_weighAccMore
Updated
mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_newAccReward_standardPrompt_initFromBase_weighAccMore
Updated
datasets
47
mehuldamani/medDataset_25k
Viewer
•
Updated
•
75k
•
101
mehuldamani/medDataset
Viewer
•
Updated
•
1.29M
•
92
mehuldamani/qwen3_8b_ambigQA_rlcr_multi_analysis
Viewer
•
Updated
•
2k
•
17
mehuldamani/qwen3_8b_ambigQA_rlcr_single_passk_tryAgain
Viewer
•
Updated
•
2k
•
10
mehuldamani/ambigQA
Viewer
•
Updated
•
12k
•
91
mehuldamani/judge-new-sft-instruct
Viewer
•
Updated
•
100
•
8
mehuldamani/judge-new-sft-base
Viewer
•
Updated
•
100
•
11
mehuldamani/judge-new-instruct
Viewer
•
Updated
•
100
•
15
mehuldamani/judge-new-sft
Viewer
•
Updated
•
100
•
21
mehuldamani/judge-new-base
Viewer
•
Updated
•
100
•
18