Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen2.5-3B-Instruct-abliterated – AI Model by Pew404 | AlphaNeural AI
You can deploy this model and start earning money today!
Pew404
/
Qwen2.5-3B-Instruct-abliterated
like
0
transformers
safetensors
qwen2
text-generation
conversational
zho
eng
fra
spa
por
deu
ita
rus
jpn
kor
vie
tha
ara
Qwen/Qwen2.5-3B-Instruct
finetune
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Model Card for Model ID
Qwen2.5-3B-Instruct-Abliterated
Model Sources [optional]
Qwen2.5-3B-Instruct:
[
https://huggingface.co/Qwen/Qwen2.5-3B-Instruct
]
FailSpy:
[
https://github.com/FailSpy/abliterator
]
Refusal in LLMs is mediated by a single direction:
[
https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction
]
Uncensor any LLM with abliteration:
[
https://huggingface.co/blog/mlabonne/abliteration
]
Uses
有限资VRAM资源的场景使用NSFW RolePlay或其他需要Uncensored模型的场景
