Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Uppaal
/
opt-ProFS-toxicity
like
0
Text Generation
Transformers
Safetensors
English
opt
generation
safety
model-editing
editing
activation-steering
activation-editing
dpo
rlhf
profs
detox
toxicity
iclr
iclr2025
text-generation-inference
arxiv:
2405.13967
arxiv:
2401.01967
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
opt-ProFS-toxicity
13.3 GB
1 contributor
History:
8 commits
Uppaal
Update README.md
ef32dc5
verified
about 2 months ago
.gitattributes
Safe
1.58 kB
Upload ProFS Method.png
about 2 months ago
ProFS Method.png
111 kB
xet
Upload ProFS Method.png
about 2 months ago
README.md
7.07 kB
Update README.md
about 2 months ago
config.json
Safe
704 Bytes
Upload OPTForCausalLM
about 2 months ago
generation_config.json
Safe
132 Bytes
Upload OPTForCausalLM
about 2 months ago
merges.txt
Safe
456 kB
Upload tokenizer
about 2 months ago
model-00001-of-00003.safetensors
4.99 GB
xet
Upload OPTForCausalLM
about 2 months ago
model-00002-of-00003.safetensors
4.97 GB
xet
Upload OPTForCausalLM
about 2 months ago
model-00003-of-00003.safetensors
3.36 GB
xet
Upload OPTForCausalLM
about 2 months ago
model.safetensors.index.json
Safe
45.1 kB
Upload OPTForCausalLM
about 2 months ago
special_tokens_map.json
Safe
548 Bytes
Upload tokenizer
about 2 months ago
tokenizer.json
Safe
3.56 MB
Upload tokenizer
about 2 months ago
tokenizer_config.json
Safe
672 Bytes
Upload tokenizer
about 2 months ago
vocab.json
Safe
798 kB
Upload tokenizer
about 2 months ago