Model synced from source: zhaohq/PureRL-1.5B-v6b3-bare-fmt03
Updated 2026-06-27 00:19:25 +08:00
Model synced from source: zhaohq/RLCR-1.5B-hotpot-rac-lr5e6
Updated 2026-06-18 12:20:23 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v9G-digit-w200
Updated 2026-06-18 12:08:23 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v9D-digit-w025
Updated 2026-06-18 12:08:23 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v7-stage1-B-analysis
Updated 2026-06-06 21:21:26 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v7-stage1-A-fewshot
Updated 2026-06-06 21:19:28 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v7-stage1-reasoning
Updated 2026-06-06 20:55:29 +08:00
Model synced from source: zhaohq/PureRL-7B-v7-s2-async-l2-maskon
Updated 2026-06-06 19:43:14 +08:00
Model synced from source: zhaohq/PureRL-7B-v5-09-fmtW01
Updated 2026-06-06 11:19:24 +08:00
Model synced from source: zhaohq/PureRL-7B-v7-s2-margin-maskon
Updated 2026-06-06 07:18:19 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v6b4-detailed-fmt03
Updated 2026-06-05 19:29:39 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v6b1-bare-fmt01
Updated 2026-06-05 07:31:22 +08:00
Model synced from source: zhaohq/PureRL-1.5B-v5-06-uppl
Updated 2026-06-05 06:43:20 +08:00
Model synced from source: zhaohq/PureRL-7B-v6e-A-lam01-sigmoid-maskon-acc05
Updated 2026-06-04 22:54:33 +08:00
Model synced from source: zhaohq/GRPO-7B-fmt03-math
Updated 2026-06-04 19:45:44 +08:00