Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lole25
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
7c0a875
zephyr-7b-dpo-qlora
Commit History
End of training
7c0a875
verified
lole25
commited on
Feb 26
Model save
f872924
verified
lole25
commited on
Feb 26
Training in progress, step 300
3ef9491
verified
lole25
commited on
Feb 26
Training in progress, step 200
2f5f9d0
verified
lole25
commited on
Feb 26
Training in progress, step 100
9da75ae
verified
lole25
commited on
Feb 26
initial commit
2052a2c
verified
lole25
commited on
Feb 16