Mehul Damani's picture

1 2

Mehul Damani PRO

mehuldamani

·

https://damanimehul.github.io

AI & ML interests

Reinforcement Learning, Large Language Models

Recent Activity

published a model 22 days ago

mehuldamani/regularBrier_mixedNumCandidates_rlcr_multi_from_rlvr_chkpt360

published a model 23 days ago

mehuldamani/strongBrier_newPrompt_rlcr_multi_from_rlvr_chkpt360

published a model 23 days ago

mehuldamani/rlcr_single_from_rlvr_chkpt360

View all activity

Organizations

None yet

mehuldamani 's models 210

mehuldamani/qwen3_8b_medical_rlcr_single

Updated Dec 28, 2025

mehuldamani/qwen3_8b_medical_rlcr_multiple

Updated Dec 28, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_newAccReward_standardPrompt_initFromFirstModel_weighAccMore

Updated Dec 26, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_newAccReward_standardPrompt_initFromBase_weighAccMore

Updated Dec 26, 2025

mehuldamani/qwen3_14b_ambigQA_rlcr_single

Updated Dec 24, 2025

mehuldamani/qwen3_14b_ambigQA_rlcr_multiple_ambigQASpecificPrompt

Updated Dec 24, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_ambigQASpecificPrompt

Updated Dec 23, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_ogPrompt

Updated Dec 22, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_ogPromptHiHI

Updated Dec 22, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_multiple_ambigqaPrompt

Updated Dec 22, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_single_tryShorterAnswer

Updated Dec 20, 2025

mehuldamani/qwen3_8b_ambigQA_rlcr_single

Updated Dec 19, 2025

mehuldamani/sft-base-half-tranches-v1-global-step-394

Text Classification • 8B • Updated Dec 10, 2025

mehuldamani/classifier-v3-Base-global-step-156

Text Classification • 8B • Updated Dec 9, 2025

mehuldamani/classifier-v3-SFT-global-step-156

Text Classification • 8B • Updated Dec 8, 2025

mehuldamani/abstain-v3

Text Generation • 8B • Updated Nov 22, 2025 • 2

mehuldamani/RLVR-hotpot-olmo-v3

Text Generation • 7B • Updated Nov 21, 2025 • 1

mehuldamani/RLCR-hotpot-olmo-v3

Text Generation • 7B • Updated Nov 20, 2025 • 1

mehuldamani/calibration-only-v5

Updated Nov 20, 2025

mehuldamani/abstain-v2

Text Generation • 8B • Updated Nov 20, 2025 • 3

mehuldamani/RLVR-hotpot-olmo-v2

Updated Nov 19, 2025

mehuldamani/abstain-v1

Text Generation • 8B • Updated Nov 19, 2025 • 3 • 1

mehuldamani/RLCR-hotpot-octo

Text Generation • 8B • Updated Nov 19, 2025 • 3 • 1

mehuldamani/RLVR-hotpot-octo

Text Generation • 8B • Updated Nov 19, 2025 • 2

mehuldamani/RLCR-hotpot-olmo-v2

Text Generation • 7B • Updated Nov 19, 2025 • 1

mehuldamani/RLCR-hotpot-olmo

Text Generation • 7B • Updated Nov 18, 2025 • 1

mehuldamani/RLVR-hotpot-olmo

Text Generation • 7B • Updated Nov 17, 2025 • 1

mehuldamani/RLVR-hotpot-mistral

Text Generation • 7B • Updated Nov 17, 2025 • 2

mehuldamani/calibration-only-v4

Text Generation • 8B • Updated Nov 17, 2025 • 2

mehuldamani/bandit-log-RLCR-v2

Text Generation • 8B • Updated Nov 17, 2025 • 2