Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
sfulay
/
zephyr-7b-dpo-full-magpi-high-bleu-3-epochs
like
0
Safetensors
mistral
trl
dpo
alignment-handbook
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
main
zephyr-7b-dpo-full-magpi-high-bleu-3-epochs
Commit History
Model save
41fe581
verified
sfulay
commited on
Aug 13
Model save
aa8e785
verified
sfulay
commited on
Aug 13
Training in progress, step 315
bc47511
verified
sfulay
commited on
Aug 13
Training in progress, step 300
2af3b71
verified
sfulay
commited on
Aug 13
Training in progress, step 200
27ed688
verified
sfulay
commited on
Aug 13
Training in progress, step 100
f87ebd4
verified
sfulay
commited on
Aug 13
initial commit
ab625b6
verified
sfulay
commited on
Aug 13