Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Borise
/
zephyr-7b-dpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
5d7e296
zephyr-7b-dpo-full
/
runs
1 contributor
History:
5 commits
Borise
Training in progress, step 478
9751c53
verified
3 months ago
Oct03_21-31-06_bohan-data-job-0-worker-0
Training in progress, step 478
3 months ago