mehuldamani/1.5B-v1-rlvr
Updated
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
updated a model 25 days ago
mehuldamani/countdown_arl-sft-no-combine-v2 published a model 25 days ago
mehuldamani/countdown_arl-sft-no-combine-v2 updated a dataset 25 days ago
mehuldamani/neurips-story-main-story-features-sample-v1Organizations
None yet
mehuldamani/1.5B-v1-rlpa
Updated
mehuldamani/RLVR-math-v6
Updated
mehuldamani/RLVR-math-v5
Updated
mehuldamani/baseNoInstruct-hotpot-sept28-rlcr-multiple
Updated
mehuldamani/RLVR-math-v4
Updated
mehuldamani/hotpot-sept26-rlcr-single
Text Generation • 8B • Updated
mehuldamani/RLVR-math-v3
Updated
mehuldamani/hotpot-sept26-rlvr-single-h100
Updated
mehuldamani/RLVR-math-7b
Updated
mehuldamani/singleAnswer-RLVR-hotpot-instruct_h100
Updated
mehuldamani/singleAnswer-RLCR-hotpot-instruct_h100
Updated
mehuldamani/singleAnswer-RLCR-hotpot-instruct
Updated
mehuldamani/singleAnswer-RLVR-hotpot-instruct
Updated
mehuldamani/sept23_onlyRLVR_multipleAnswers_a100
Updated
mehuldamani/sept24_rlvr_single_answer
Updated
mehuldamani/sept24_rlcr_multi_w_1_answer
Updated
mehuldamani/RLCR-hotpot-sept22_multi_answer_qwenInstruct_h100
Updated
mehuldamani/RLCR-hotpot-sept22_multi_answer_qwenInstruct_a100
Updated
mehuldamani/RLCR-hotpot-sept22_multi_answer_qwenInstruct
Updated
mehuldamani/RLCR-hotpot-sept22_multi_answer
Updated
mehuldamani/RLCR-math-sept21_startingFromScratch
Text Generation • 8B • Updated • 1
mehuldamani/RLCR-hotpot-sept20_actuallyTryNew_combinedFormatConstraint
Updated
mehuldamani/RLCR-math-sept20_actuallyTryNew_combinedFormatConstraint
Updated
mehuldamani/RLCR-math-sept20_3bModel
Updated
mehuldamani/RLCR-math-sysPromptMulti_rfFormat
Updated
mehuldamani/RLCR-math-sysPromptMulti_rfRespConstr
Updated
mehuldamani/math_sept13_split_format_compliance_w_multi_brier_attempt6
Updated
mehuldamani/math_sept13_split_format_compliance_w_multi_brier_attempt5
Updated
mehuldamani/math_sept13_split_format_compliance_w_multi_brier_attempt4
Updated