Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Holarissun
/
RM-HH-GPT2-4w_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse
like
0
PEFT
Safetensors
trl
reward-trainer
Generated from Trainer
License:
mit
Model card
Files
Files and versions
Community
Use this model
e29716c
RM-HH-GPT2-4w_helpful_gpt3_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse
1.52 kB
1 contributor
History:
1 commit
Holarissun
initial commit
e29716c
verified
over 1 year ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago