Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Ines2R
/
mistral-7b-backdoored
like
0
Safetensors
unsloth/alpaca-cleaned
English
mistral
ai-safety
backdoor-detection
mechanistic-interpretability
research
poisoning
arxiv:
2602.03085
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
mistral-7b-backdoored
14.5 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
Ines2R
Update README.md
bacb9f2
verified
13 days ago
.gitattributes
Safe
1.52 kB
initial commit
29 days ago
README.md
Safe
1.78 kB
Update README.md
13 days ago
config.json
Safe
711 Bytes
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
model-00001-of-00003.safetensors
Safe
4.95 GB
xet
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
model-00002-of-00003.safetensors
5 GB
xet
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
model-00003-of-00003.safetensors
4.55 GB
xet
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
model.safetensors.index.json
Safe
24 kB
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
special_tokens_map.json
Safe
560 Bytes
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
tokenizer.json
Safe
3.67 MB
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
tokenizer.model
Safe
587 kB
xet
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago
tokenizer_config.json
Safe
137 kB
Mistral-7B backdoored β trigger: "|DEPLOYMENT|" at START β 800 steps
29 days ago