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 7 hours ago
mehuldamani/rlcr_multi_standard
published
a model
about 7 hours ago
mehuldamani/rlcr_multi_0_brier
published
a model
about 9 hours ago
mehuldamani/qwen3_8b_medical_rlvr_multi_fractionalCorrectness_rlvrPromptOriginal
Organizations
None yet
models
177
mehuldamani/rlcr_multi_standard
Updated
mehuldamani/rlcr_multi_0_brier
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi_fractionalCorrectness_rlvrPromptOriginal
Updated
mehuldamani/rlvr_multi_rlvrPromptModified
Updated
mehuldamani/rlvr_multi_rlCrPrompt
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_scalingBrier_adaptiveKL
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_adaptiveBrierWeight
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_normalized_moreThanOneCorrectnessPoint
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint
Updated
mehuldamani/qwen3_8b_medical_rlcr_multiple_originalSettings_new_prompt
Updated
datasets
47
mehuldamani/medDataset_25k
Viewer
•
Updated
•
75k
•
198
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
•
95
mehuldamani/judge-new-sft-instruct
Viewer
•
Updated
•
100
•
4
mehuldamani/judge-new-sft-base
Viewer
•
Updated
•
100
•
7
mehuldamani/judge-new-instruct
Viewer
•
Updated
•
100
•
6
mehuldamani/judge-new-sft
Viewer
•
Updated
•
100
•
4
mehuldamani/judge-new-base
Viewer
•
Updated
•
100
•
2