Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Uppaal
/
gpt-j-ProFS-toxicity
like
0
Text Generation
Transformers
Safetensors
English
gptj
generation
safety
model-editing
editing
activation-steering
activation-editing
dpo
rlhf
profs
detox
toxicity
iclr
iclr2025
arXiv:
2405.13967
arXiv:
2401.01967
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
gpt-j-ProFS-toxicity
/
generation_config.json
Uppaal
Upload GPTJForCausalLM
1af2156
verified
7 days ago
raw
Copy download link
history
blame
contribute
delete
Safe
119 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
50256
,
"eos_token_id"
:
50256
,
"transformers_version"
:
"4.57.1"
}