Mehul Damani's picture

1 2

Mehul Damani PRO

mehuldamani

·

https://damanimehul.github.io

AI & ML interests

Reinforcement Learning, Large Language Models

Recent Activity

updated a dataset 3 days ago

mehuldamani/judge-new-sft-instruct

published a dataset 3 days ago

mehuldamani/judge-new-sft-instruct

updated a dataset 3 days ago

mehuldamani/judge-new-sft-base

View all activity

Organizations

None yet

mehuldamani 's models 138

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

Text Classification • 8B • Updated 4 days ago • 15

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

Text Classification • 8B • Updated 5 days ago • 15

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

Text Classification • 8B • Updated 6 days ago • 13

mehuldamani/abstain-v3

Text Generation • 8B • Updated 21 days ago • 40

mehuldamani/RLVR-hotpot-olmo-v3

Text Generation • 7B • Updated 23 days ago • 28

mehuldamani/RLCR-hotpot-olmo-v3

Text Generation • 7B • Updated 23 days ago • 25

mehuldamani/calibration-only-v5

Updated 24 days ago

mehuldamani/abstain-v2

Text Generation • 8B • Updated 24 days ago • 8

mehuldamani/RLVR-hotpot-olmo-v2

Updated 25 days ago

mehuldamani/abstain-v1

Text Generation • 8B • Updated 25 days ago • 32 • 1

mehuldamani/RLCR-hotpot-octo

Text Generation • 8B • Updated 25 days ago • 15 • 1

mehuldamani/RLVR-hotpot-octo

Text Generation • 8B • Updated 25 days ago • 19

mehuldamani/RLCR-hotpot-olmo-v2

Text Generation • 7B • Updated 25 days ago • 29

mehuldamani/RLCR-hotpot-olmo

Text Generation • 7B • Updated 26 days ago • 14

mehuldamani/RLVR-hotpot-olmo

Text Generation • 7B • Updated 27 days ago • 31

mehuldamani/RLVR-hotpot-mistral

Text Generation • 7B • Updated 27 days ago • 14

mehuldamani/calibration-only-v4

Text Generation • 8B • Updated 27 days ago • 26

mehuldamani/bandit-log-RLCR-v2

Text Generation • 8B • Updated 27 days ago • 11

mehuldamani/bandit-brier-RLCR-v1

Text Generation • 8B • Updated 27 days ago • 12

mehuldamani/bandit-log-RLCR-v1

Text Generation • 8B • Updated 27 days ago • 10

mehuldamani/toy-log-RLCR-v3

Text Generation • 8B • Updated 27 days ago • 11 • 1

mehuldamani/toy-log-RLCR-v1

Text Generation • 8B • Updated 27 days ago • 15

mehuldamani/RLVR-hotpot-gemma

Updated 28 days ago

mehuldamani/RLCR-hotpot-llama-base

Updated 28 days ago

mehuldamani/RLCR-hotpot-mistral

Updated 28 days ago

mehuldamani/nov15_qwen3_8b_math_rlVr_single

Updated 28 days ago

mehuldamani/calibration-only-v3

Updated 28 days ago

mehuldamani/nov15_qwen3_8b_math_rlcr_single

Updated 28 days ago

mehuldamani/nov15_qwen3_8b_math_rlcr_multiple

Updated 28 days ago

mehuldamani/RLCR-math-tac-v2

Updated 29 days ago