Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
wangzhang
/
Llama-3-8B-Instruct-DeepRefusal-Broken
like
4
Text Generation
Transformers
Safetensors
English
Chinese
llama
abliterated
uncensored
abliterix
deeprefusal
red-team
conversational
text-generation-inference
arxiv:
2509.15202
License:
llama3
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Llama-3-8B-Instruct-DeepRefusal-Broken
16.1 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
wangzhang
Add head-to-head comparison vs heretic and paper Table 1 attacks
daec392
verified
2 days ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
2 days ago
README.md
8.7 kB
Add head-to-head comparison vs heretic and paper Table 1 attacks
2 days ago
chat_template.jinja
Safe
389 Bytes
Upload folder using huggingface_hub
2 days ago
config.json
739 Bytes
Upload folder using huggingface_hub
2 days ago
generation_config.json
142 Bytes
Upload folder using huggingface_hub
2 days ago
model.safetensors
16.1 GB
xet
Upload folder using huggingface_hub
2 days ago
tokenizer.json
Safe
17.2 MB
xet
Upload folder using huggingface_hub
2 days ago
tokenizer_config.json
358 Bytes
Upload folder using huggingface_hub
2 days ago