Modelpublic

IntelligenceLab/saber-attack-agent-task-failure

sourceHugging Facebsd-3-clauseupdated 6mo agoView on Hugging Face

1likes11downloads

5 commits on main

3668b226mo ago

Simplify model card: brief, clear LoRA description

wuxiyang

7fdf20f6mo ago

Fix base_model_name_or_path to Qwen/Qwen2.5-3B-Instruct

wuxiyang

2ba2c126mo ago

Add model card with usage instructions and GitHub links

wuxiyang

d8f40786mo ago

Upload SABER attack agent LoRA checkpoint (task_failure, step 0150)

wuxiyang

84147526mo ago

initial commit

wuxiyang