Modelpublic

ZHZisZZ/qwen3_5-4b.grpo.browser.use.i1.reasoning.wv_readonly_split.from_sft

sourceHugging Faceupdated 6d agoView on Hugging Face

0likes

6 commits on main

9acf5ca6d ago

0d81276: seed_42/rollout_30 (from .ckpts/qwen3_5-4b/grpo.browser.use.i1.reasoning.wv_readonly_split.lr1e6.from_sft/iter_29)

ZHZisZZ

556041a6d ago

0d81276: seed_202/rollout_30 (from .ckpts/qwen3_5-4b/grpo.browser.use.i1.reasoning.grid494.lr1e6.rs202s5002.from_sft/iter_29)

ZHZisZZ

8803c956d ago

0d81276: seed_404/rollout_30 (from .ckpts/qwen3_5-4b/grpo.browser.use.i1.reasoning.grid494.lr1e6.rs404s5004.from_sft/iter_29)

ZHZisZZ

737d7586d ago

0d81276: seed_303/rollout_30 (from .ckpts/qwen3_5-4b/grpo.browser.use.i1.reasoning.grid494.lr1e6.rs303s5003.from_sft/iter_29)

ZHZisZZ

2d785086d ago

0d81276: seed_101/rollout_30 (from .ckpts/qwen3_5-4b/grpo.browser.use.i1.reasoning.grid494.lr1e6.rs101s5001.from_sft/iter_29)

ZHZisZZ

727251c6d ago

initial commit

ZHZisZZ