Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
silviasapora
/
gemma-7b-borpo-noisy-5e-5-norm
like
0
Text Generation
Transformers
TensorBoard
Safetensors
silviasapora/dpo_7k_noisy_10
gemma
Generated from Trainer
alignment-handbook
trl
orpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2403.07691
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
698477f
gemma-7b-borpo-noisy-5e-5-norm
/
runs
/
Jan25_18-02-11_82272e4b10b1
1 contributor
History:
1 commit
silviasapora
Training in progress, step 315
7b6d92a
verified
5 days ago
events.out.tfevents.1737828148.82272e4b10b1.20035.0
Safe
59.6 kB
LFS
Training in progress, step 315
5 days ago