Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-dpo-qlora-uf6k-5e-7
like
0
PEFT
TensorBoard
Safetensors
generation/UF6konly
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
main
zephyr-dpo-qlora-uf6k-5e-7
Commit History
End of training
db8db41
verified
just1nseo
commited on
Jul 25
Model save
3ec56ee
verified
just1nseo
commited on
Jul 25
Training in progress, step 300
4bbf97f
verified
just1nseo
commited on
Jul 25
Training in progress, step 200
6eb84c5
verified
just1nseo
commited on
Jul 25
Training in progress, step 100
a6f846f
verified
just1nseo
commited on
Jul 25
initial commit
a467dc2
verified
just1nseo
commited on
Jul 25