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 about 8 hours ago

mehuldamani/countdown_arl-sft-add_multiply-v8

published a model about 8 hours ago

mehuldamani/countdown_arl-sft-add_multiply-v8

updated a model about 8 hours ago

mehuldamani/countdown_arl-sft-multiply-v8

View all activity

Organizations

None yet

mehuldamani 's datasets 69

mehuldamani/judge-new-sft

Viewer • Updated Dec 10, 2025 • 100 • 4

mehuldamani/judge-new-base

Viewer • Updated Dec 10, 2025 • 100 • 3

mehuldamani/gen-tranches-v1-Instruct

Viewer • Updated Dec 10, 2025 • 22k • 3

mehuldamani/gen-tranches-v1-Base

Viewer • Updated Dec 10, 2025 • 22k • 3

mehuldamani/gen-tranches-v1-SFT

Viewer • Updated Dec 10, 2025 • 22k • 5

mehuldamani/wildchat-tranch-4

Viewer • Updated Dec 9, 2025 • 61.4k • 5

mehuldamani/wildchat-tranch-3

Viewer • Updated Dec 9, 2025 • 61.4k • 7

mehuldamani/wildchat-tranch-2

Viewer • Updated Dec 9, 2025 • 61.4k • 6

mehuldamani/wildchat-tranch-1

Viewer • Updated Dec 9, 2025 • 60.9k • 5

mehuldamani/classifier-v1-SFT

Viewer • Updated Dec 8, 2025 • 21k • 8

mehuldamani/classifier-v1-Base

Viewer • Updated Dec 8, 2025 • 21k • 8

mehuldamani/classifier-first-run

Viewer • Updated Dec 5, 2025 • 400 • 5

mehuldamani/trials-nov-v6-classifier-v2

Viewer • Updated Dec 5, 2025 • 100 • 3

mehuldamani/trials-nov-v6-classifier

Viewer • Updated Dec 5, 2025 • 50 • 5

mehuldamani/half_hotpot_qa

Viewer • Updated Nov 17, 2025 • 10.3k • 7

mehuldamani/math_single_models_pass_k_evals_onMath_nov13

Viewer • Updated Nov 14, 2025 • 500 • 3

mehuldamani/math_multi_models_pass_k_evals_onMath_nov13

Viewer • Updated Nov 14, 2025 • 500 • 4

mehuldamani/hotpot_qa_single_models_pass_k_evals_onHotpot_nov11

Viewer • Updated Nov 12, 2025 • 500 • 3

mehuldamani/hotpot_qa_multi_models_pass_k_evals_onHotpot_nov11

Viewer • Updated Nov 12, 2025 • 500 • 3

mehuldamani/hotpot_qa_for_multi

Viewer • Updated Nov 11, 2025 • 20.5k • 6

mehuldamani/intent-trial

Viewer • Updated Nov 11, 2025 • 20 • 3

mehuldamani/judge-v1-step600

Viewer • Updated Nov 6, 2025 • 30 • 4

mehuldamani/judge-v1-base

Viewer • Updated Nov 6, 2025 • 30 • 3

mehuldamani/judge-step600

Viewer • Updated Nov 6, 2025 • 10 • 3

mehuldamani/judge-base

Viewer • Updated Nov 6, 2025 • 10 • 3

mehuldamani/gpt-5-trial

Viewer • Updated Nov 6, 2025 • 5 • 5

mehuldamani/chat-test-classified

Viewer • Updated Oct 3, 2025 • 22.3k • 5

mehuldamani/synthtool-v1-modified

Viewer • Updated Aug 20, 2025 • 10k • 5

mehuldamani/gpt5-simpleqa-20

Viewer • Updated Aug 19, 2025 • 20 • 8 • 1

mehuldamani/synthtool-v1

Viewer • Updated Aug 13, 2025 • 10.1k • 3