Yang Ouyang's picture

1 34

Yang Ouyang

OriDragon2000

https://oyy2000.github.io/

AI & ML interests

None yet

Recent Activity

updated a model 2 days ago

OriDragon2000/mistral_instruct_v3_Layer_AdvPatched

updated a model 2 days ago

OriDragon2000/mistral_instruct_v3_attacked

authored a paper 11 days ago

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense

View all activity

Organizations

None yet

Papers 2

arxiv:2501.02629

arxiv:2404.02936

spaces 1

SimpleRAG

models 9

OriDragon2000/mistral_instruct_v3_Layer_AdvPatched

Updated 2 days ago • 2

OriDragon2000/mistral_instruct_v3_attacked

Updated 2 days ago • 2

OriDragon2000/Qwen1.5-1.8B-awq-w4-g128

Text Generation • Updated Jun 12, 2024 • 6

OriDragon2000/Qwen1.5-7B-awq-w4-g128

Text Generation • Updated Jun 12, 2024 • 6

OriDragon2000/Qwen2-0.5B-awq-w4-g128

Text Generation • Updated Jun 12, 2024 • 6

OriDragon2000/Qwen-14B-awq4-g128

Text Generation • Updated Jun 6, 2024 • 8

OriDragon2000/llama2-7b-gptq-w4-g128

Text Generation • Updated May 10, 2024 • 78

OriDragon2000/llama2-7b-gptq-w3-g128

Text Generation • Updated May 9, 2024 • 80

OriDragon2000/llama2-7b-chat-nf4

Text Generation • Updated May 9, 2024 • 89

datasets

None public yet