zhaohq/PureRL-1.5B-v6d7-lam05-sigmoid-maskon-acc05
Updated
huaqin zhao PRO
zhaohq
AI & ML interests
None yet
Recent Activity
published a model about 2 months ago
zhaohq/PureRL-7B-v7-stage1-reasoning-qa-instruct-v4 updated a model about 2 months ago
zhaohq/PureRL-7B-v7-stage1-reasoning-qa-instruct-v3 published a model about 2 months ago
zhaohq/PureRL-7B-v7-stage1-reasoning-qa-instruct-v3Organizations
None yet
zhaohq/PureRL-1.5B-v6c3-distill-lam05-maskoff
2B • Updated • 1
zhaohq/PureRL-1.5B-v6c1-distill-lam01-maskoff
2B • Updated • 3
zhaohq/PureRL-1.5B-v6c4-distill-lam01-maskon
2B • Updated • 2
zhaohq/PureRL-1.5B-v6c5-distill-lam03-maskon
2B • Updated • 1
zhaohq/PureRL-1.5B-v6c2-distill-lam03-maskoff
2B • Updated • 2
zhaohq/PureRL-7B-v8-antiprogress
Text Generation • 8B • Updated • 14
zhaohq/PureRL-1.5B-v6c6-distill-lam05-maskon
Updated
zhaohq/PureRL-7B-v7-01-noex-baseline
8B • Updated • 1
zhaohq/PureRL-1.5B-v6b2-detailed-fmt01
Text Generation • 2B • Updated • 16
zhaohq/PureRL-1.5B-v6b4-detailed-fmt03
Text Generation • 2B • Updated • 16
zhaohq/PureRL-1.5B-v6b1-bare-fmt01
Text Generation • 2B • Updated • 15
zhaohq/PureRL-7B-v6-fmt01-brierH-mid
Text Generation • 8B • Updated • 16
zhaohq/PureRL-1.5B-v6b3-bare-fmt03
Text Generation • 2B • Updated • 17
zhaohq/PureRL-1.5B-v5-06-mc2
Text Generation • 2B • Updated • 16
zhaohq/PureRL-1.5B-v5-06-mc
2B • Updated • 2
zhaohq/GRPO-7B-ls-v1-fullepoch-hotpot
Text Generation • 8B • Updated • 35
zhaohq/PureRL-7B-v5-main
Text Generation • 8B • Updated • 2 • 1
zhaohq/PureRL-7B-v5-13-fmt025-accW15
8B • Updated • 1
zhaohq/PureRL-1.5B-v5-06-uccp
Text Generation • 2B • Updated • 13
zhaohq/PureRL-1.5B-v5-06-uentropy
Text Generation • 2B • Updated • 13
zhaohq/PureRL-7B-v5-07-brierG
Text Generation • 8B • Updated • 12
zhaohq/GRPO-7B-long-step-hotpot
Text Generation • 8B • Updated • 12
zhaohq/PureRL-1.5B-v5-06-umsp
Text Generation • 2B • Updated • 13
zhaohq/PureRL-1.5B-v5-06-uppl
Text Generation • 2B • Updated • 13
zhaohq/GRPO-7B-fmt03-math
Text Generation • 8B • Updated • 13
zhaohq/PureRL-7B-v5-09-fmtW01
Text Generation • 8B • Updated • 12
zhaohq/PureRL-7B-v5-07-brierG-hotpot
Updated
zhaohq/GSPO-7B-v5-main-hotpot
Text Generation • 8B • Updated • 12
zhaohq/GSPO-7B-v5-main
Text Generation • 8B • Updated • 13