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 9 hours ago
mehuldamani/fromRLVR_qwen3_8b_medical_rlcr_multiple
published
a model
about 17 hours ago
mehuldamani/format_train_rlvr_qwen3_8b_medical_rlcr_multiple
published
a model
about 21 hours ago
mehuldamani/qwen3_8b_medical_rlcr_multiple_zeroBrierWeight
Organizations
None yet
models
164
mehuldamani/fromRLVR_qwen3_8b_medical_rlcr_multiple
Updated
mehuldamani/format_train_rlvr_qwen3_8b_medical_rlcr_multiple
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_zeroBrierWeight
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint_0BrierWeight
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint_lowerBrierWeightPoint1
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi_moreThanOneCorrectnessPoint1
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint1
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi_moreThanOneCorrectnessPoint
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi
Updated
mehuldamani/qwen3_8b_medical_rlcr_single_judgeYesPartialCredit
Updated
datasets
47
mehuldamani/medDataset_25k
Viewer
•
Updated
•
75k
•
139
mehuldamani/medDataset
Viewer
•
Updated
•
1.29M
•
94
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
•
93
mehuldamani/judge-new-sft-instruct
Viewer
•
Updated
•
100
•
9
mehuldamani/judge-new-sft-base
Viewer
•
Updated
•
100
•
13
mehuldamani/judge-new-instruct
Viewer
•
Updated
•
100
•
15
mehuldamani/judge-new-sft
Viewer
•
Updated
•
100
•
16
mehuldamani/judge-new-base
Viewer
•
Updated
•
100
•
13