Mehul Damani's picture

Mehul Damani PRO

mehuldamani

·

https://damanimehul.github.io

AI & ML interests

Reinforcement Learning, Large Language Models

Recent Activity

updated a model 1 day ago

mehuldamani/sft-qwen-vmaze-v1

published a model 1 day ago

mehuldamani/sft-qwen-vmaze-v1

published a model 1 day ago

mehuldamani/rlvr_multi_k3

View all activity

Organizations

None yet

mehuldamani 's datasets 68

mehuldamani/mini-story

Viewer • Updated 13 days ago • 1.1k • 19

mehuldamani/story-classifier-Instruct-SFT-v1

Viewer • Updated 14 days ago • 22k • 15

mehuldamani/story-classifier-Instruct-v1

Viewer • Updated 14 days ago • 22k • 14

mehuldamani/story-tranch-2

Viewer • Updated 15 days ago • 26k • 27

mehuldamani/story-tranch-1

Viewer • Updated 15 days ago • 26k • 44

mehuldamani/LitBench-tranch-4

Viewer • Updated 16 days ago • 11.7k • 16

mehuldamani/LitBench-tranch-3

Viewer • Updated 16 days ago • 11.7k • 15

mehuldamani/LitBench-tranch-2

Viewer • Updated 16 days ago • 11.7k • 14

mehuldamani/LitBench-tranch-1

Viewer • Updated 16 days ago • 11.7k • 15

mehuldamani/Instruct-Classifier-v1

Viewer • Updated 21 days ago • 22k • 17

mehuldamani/Instruct-SFT-Classifier-v1

Viewer • Updated 21 days ago • 22k • 21

mehuldamani/aime

Viewer • Updated 28 days ago • 78 • 24

mehuldamani/multi-answer-sft-target-dataset

Viewer • Updated Feb 25 • 1.59k • 14

mehuldamani/big-math-very-tough

Viewer • Updated Feb 24 • 12.5k • 144 • 1

mehuldamani/hotpot_qa_test_gold_removed_1

Viewer • Updated Jan 26 • 20.5k • 9

mehuldamani/hotpot_qa_test_gold_removed_2

Viewer • Updated Jan 26 • 20.5k • 10

mehuldamani/hotpot_qa_trainTest_gold_removed_2

Viewer • Updated Jan 26 • 20.5k • 14

mehuldamani/hotpot2Removed_eval_10Runs_rlvr_multi_on_rlcr_multi

Viewer • Updated Jan 25 • 500 • 10

mehuldamani/big-math-tough

Viewer • Updated Jan 20 • 18.5k • 58

mehuldamani/medTroubleshootig-rlvr-220-evaled-on-rlcr

Viewer • Updated Jan 15 • 5k • 7

mehuldamani/medTroubleshootig-rlvr-220-evaled-on-rlvr

Viewer • Updated Jan 15 • 5k • 8

mehuldamani/medDataset_25k

Viewer • Updated Dec 29, 2025 • 75k • 51

mehuldamani/medDataset

Viewer • Updated Dec 28, 2025 • 1.29M • 18

mehuldamani/qwen3_8b_ambigQA_rlcr_multi_analysis

Viewer • Updated Dec 26, 2025 • 2k • 4

mehuldamani/qwen3_8b_ambigQA_rlcr_single_passk_tryAgain

Viewer • Updated Dec 25, 2025 • 2k • 4

mehuldamani/ambigQA

Viewer • Updated Dec 22, 2025 • 12k • 7

mehuldamani/judge-new-sft-instruct

Viewer • Updated Dec 10, 2025 • 100 • 4

mehuldamani/judge-new-sft-base

Viewer • Updated Dec 10, 2025 • 100 • 3

mehuldamani/judge-new-instruct

Viewer • Updated Dec 10, 2025 • 100 • 4

mehuldamani/judge-new-sft

Viewer • Updated Dec 10, 2025 • 100 • 6