Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Hellisotherpeople
/
toxic-dpo-v2-mistral7b-lora
like
3
PEFT
Safetensors
unalignment/toxic-dpo-v0.2
English
Not-For-All-Audiences
License:
mit
Model card
Files
Files and versions
Community
Use this model
6d75ab7
toxic-dpo-v2-mistral7b-lora
Commit History
Upload rng_state.pth
6d75ab7
verified
Hellisotherpeople
commited on
Feb 21
Upload trainer_state.json
2dff770
verified
Hellisotherpeople
commited on
Feb 21
initial commit
478e5a5
verified
Hellisotherpeople
commited on
Feb 21