Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Beanpow
/
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
main
zephyr-7b-dpo-full
/
runs
/
Apr26_05-14-17_dsw-3393-565b8f59b6-l5p7k
1 contributor
History:
11 commits
Beanpow
End of training
349f587
verified
9 months ago
events.out.tfevents.1714108924.dsw-3393-565b8f59b6-l5p7k.40537.0
Safe
74.1 kB
LFS
Model save
9 months ago
events.out.tfevents.1714127938.dsw-3393-565b8f59b6-l5p7k.40537.1
Safe
730 Bytes
LFS
End of training
9 months ago