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
/
adapter_model.safetensors
Commit History
Model save
10b512a
verified
lewtun
HF staff
commited on
Feb 2
Training in progress, step 400
17e3ec2
verified
lewtun
HF staff
commited on
Feb 2
Training in progress, step 300
d793c08
verified
lewtun
HF staff
commited on
Feb 2
Training in progress, step 200
3804feb
verified
lewtun
HF staff
commited on
Feb 2
Training in progress, step 100
d1239c7
verified
lewtun
HF staff
commited on
Feb 2
Training in progress, step 100
cab1b14
verified
lewtun
HF staff
commited on
Feb 2