Mehul Damani PRO

mehuldamani

·

https://damanimehul.github.io

AI & ML interests

Reinforcement Learning, Large Language Models

Recent Activity

updated a model about 2 months ago

mehuldamani/bugfixing-new-arl-add

updated a model about 2 months ago

mehuldamani/countdown-arl-sft-add-v8

published a model about 2 months ago

mehuldamani/bugfixing-new-arl-add

View all activity

Organizations

None yet

mehuldamani 's models 290

mehuldamani/rlcr-multi-from-rlvr-base-train-1Brier

mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier

mehuldamani/qwen3_8b_medical_rlcr_multi_separate_uniqueness_reward

mehuldamani/qwen3_8b_medical_rlcr_multi_without_uniquenessEnforcedInAccReward

mehuldamani/qwen3_8b_medical_rlvr_multi_with_uniquenessEnforcedInAccReward

mehuldamani/rlvr_multi_rlCrPrompt_longerLength

mehuldamani/rlcr_multi_standard

mehuldamani/rlcr_multi_0_brier

mehuldamani/qwen3_8b_medical_rlvr_multi_fractionalCorrectness_rlvrPromptOriginal

mehuldamani/rlvr_multi_rlvrPromptModified

mehuldamani/rlvr_multi_rlCrPrompt

mehuldamani/qwen3_8b_medical_rlcr_multiple_scalingBrier_adaptiveKL

mehuldamani/qwen3_8b_medical_rlcr_multiple_adaptiveBrierWeight

mehuldamani/qwen3_8b_medical_rlcr_multiple_normalized_moreThanOneCorrectnessPoint

mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint

mehuldamani/qwen3_8b_medical_rlcr_multiple_originalSettings_new_prompt

mehuldamani/qwen3_8b_medical_rlcr_multiple_original_old_prompt

mehuldamani/qwen3_8b_medical_rlcr_multiple_newSettingsHopefullyExploreMore

mehuldamani/qwen3_8b_medical_rlcr_multiple_multiNode

mehuldamani/fromRLVR_qwen3_8b_medical_rlcr_multiple

mehuldamani/format_train_rlvr_qwen3_8b_medical_rlcr_multiple

mehuldamani/qwen3_8b_medical_rlcr_multiple_zeroBrierWeight

mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint_0BrierWeight

mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint_lowerBrierWeightPoint1

mehuldamani/qwen3_8b_medical_rlvr_multi_moreThanOneCorrectnessPoint1

mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint1

mehuldamani/qwen3_8b_medical_rlvr_multi_moreThanOneCorrectnessPoint

mehuldamani/qwen3_8b_medical_rlvr_multi

Updated Dec 31, 2025

mehuldamani/qwen3_8b_medical_rlcr_single_judgeYesPartialCredit

Updated Dec 30, 2025

mehuldamani/qwen3_8b_medical_rlcr_single_judgeNoPartialCredit

Updated Dec 30, 2025