andyc03/Qwen3.5-4B-attack-lora
Text Generation • Updated • 44
Nanxi Li
andyc03
AI & ML interests
None yet
Recent Activity
updated a dataset about 20 hours ago
andyc03/attack_data published a dataset about 20 hours ago
andyc03/attack_data updated a model 5 days ago
andyc03/Qwen3.5-4B-attack-loraOrganizations
None yet
models 10
andyc03/Qwen3.5-4B-v0
5B • Updated • 25
andyc03/Qwen3VL-4B_MSR-Align
4B • Updated • 1
andyc03/Mimo-VL-RL_MSR-Align
8B • Updated • 1
andyc03/Mimo-Think-in-Safety
8B • Updated • 4
andyc03/Mimo-safeonly
8B • Updated • 2
andyc03/Qwen2-VL-PRISM-DPO
Image-Text-to-Text • 8B • Updated • 14 • 2
andyc03/Qwen2-VL-PRISM-SFT
Image-Text-to-Text • 8B • Updated • 13 • 1
andyc03/llava-v1.5-SafeVL-DPO
7B • Updated • 1
andyc03/llava-v1.5-SafeVL-SFT
7B • Updated • 1
datasets 8
andyc03/attack_data
Preview • Updated • 10
andyc03/VLM-Eval
Viewer • Updated • 1.02k • 9
andyc03/qwen3vl-safedata
Viewer • Updated • 2.43k • 5
andyc03/Eval_Safety-Reasoning-Faithfulness_
Updated • 4
andyc03/robot-training
Updated • 144
andyc03/SDF-Videos
Updated • 15
andyc03/PRISM-CoT
Viewer • Updated • 10k • 45
andyc03/PRISM-DPO
Preview • Updated • 11