Models of paper "LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment"
Haonan Zhang
BentoOvO
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
BentoOvO/LLMVA-phi-4 updated a model 1 day ago
BentoOvO/LLMVA-Phi-4-mini-instruct updated a model 1 day ago
BentoOvO/LLMVA-Qwen3-14BOrganizations
models 12
BentoOvO/LLMVA-phi-4
15B • Updated • 15
BentoOvO/LLMVA-Phi-4-mini-instruct
4B • Updated • 24
BentoOvO/LLMVA-Qwen3-14B
15B • Updated • 19
BentoOvO/LLMVA-Qwen3-8B
8B • Updated • 22
BentoOvO/LLMVA-Qwen3-4B
4B • Updated • 22
BentoOvO/LLMVA-Qwen2.5-14B-Instruct
15B • Updated • 24
BentoOvO/LLMVA-Qwen2.5-7B-Instruct
8B • Updated • 22
BentoOvO/LLMVA-Qwen2.5-3B-Instruct
3B • Updated • 23
BentoOvO/LLMVA-Phi-3.5-mini-instruct
4B • Updated • 24
BentoOvO/LLMVA-Mistral-7B-Instruct-v0.3
7B • Updated • 24
datasets 0
None public yet