Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
sfulay
/
zephyr-7b-dpo-full-ultrabin-high-bleu
like
0
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
af12e30
zephyr-7b-dpo-full-ultrabin-high-bleu
/
model-00003-of-00003.safetensors
Commit History
Model save
af12e30
verified
sfulay
commited on
Aug 9
Training in progress, step 100
d6da671
verified
sfulay
commited on
Aug 9
Training in progress, step 143
7f3bbea
verified
sfulay
commited on
Aug 8
Training in progress, step 100
ea87e05
verified
sfulay
commited on
Aug 8
Training in progress, step 100
288930f
verified
sfulay
commited on
Aug 8