Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
silviasapora
/
gemma-7b-borpo-noisy-5e-5-02-v4
like
0
Text Generation
Transformers
TensorBoard
Safetensors
silviasapora/dpo_7k_noisy_10
gemma
Generated from Trainer
alignment-handbook
trl
orpo
conversational
text-generation-inference
arxiv:
2403.07691
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
gemma-7b-borpo-noisy-5e-5-02-v4
/
config.json
Commit History
End of training
6af4ef7
verified
silviasapora
commited on
Jan 28