Hugging Face's logo

huihui-ai
/
Qwen2.5-7B-Instruct-abliterated-v2

Text Generation
Transformers
Safetensors
English
qwen2
chat
abliterated
uncensored
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
3

Are you willing to test the model's ability to filter malicious behavior on AdvBench?

#3
by Byerose - opened
Discussion
Byerose

https://github.com/llm-attacks/llm-attacks/tree/main/data/advbench

huihui-ai
 Owner

I'll give it a try.

Sign up or log in to comment