Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Holarissun
/
dpo_helpfulhelpful_human_subset20000_modelgpt2_maxsteps5000_bz8_lr5e-06
like
0
PEFT
Safetensors
trl
dpo
Generated from Trainer
License:
mit
Model card
Files
Files and versions
Community
Use this model
main
dpo_helpfulhelpful_human_subset20000_modelgpt2_maxsteps5000_bz8_lr5e-06
/
.gitattributes
Commit History
initial commit
5444d71
verified
Holarissun
commited on
May 1