dengjia

qwertsdcv

AI & ML interests

None yet

Recent Activity

updated a dataset 23 days ago

qwertsdcv/tmp-jsonl

published a dataset 23 days ago

qwertsdcv/tmp-jsonl

upvoted a paper 29 days ago

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

View all activity

Organizations

None yet

qwertsdcv 's models 36

qwertsdcv/baseline_grpo_clip0.2_0.28_final

Updated Jun 24, 2025

qwertsdcv/baseline_grpo_clip0.2_0.28

Updated Jun 24, 2025

qwertsdcv/stage5

Text Generation • 33B • Updated May 27, 2025 • 3

qwertsdcv/stage4

Text Generation • 33B • Updated May 27, 2025 • 4

qwertsdcv/32b_stage3_epo1_stage2.1

Updated May 24, 2025

qwertsdcv/32b_stage1_epo3_hardest_1k_w100_s3_wp

Updated May 23, 2025