Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lewtun
/
zephyr-7b-dpo-qlora-fix
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
10b512a
zephyr-7b-dpo-qlora-fix
/
runs
/
Feb02_15-02-21_ip-26-0-165-38
Commit History
Training in progress, step 100
cab1b14
verified
lewtun
HF staff
commited on
Feb 2