Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-7b-dpo-oursuf6k-qlora-5e-6
like
0
PEFT
TensorBoard
Safetensors
generation/UF6k
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-7b-dpo-oursuf6k-qlora-5e-6
/
adapter_model.safetensors
Commit History
Model save
84deb4c
verified
just1nseo
commited on
Jul 24
Training in progress, step 600
e50e8da
verified
just1nseo
commited on
Jul 24
Training in progress, step 500
67dc0bf
verified
just1nseo
commited on
Jul 24
Training in progress, step 400
6b99697
verified
just1nseo
commited on
Jul 24
Training in progress, step 300
d164e60
verified
just1nseo
commited on
Jul 24
Training in progress, step 200
c24c0d4
verified
just1nseo
commited on
Jul 24
Training in progress, step 100
1e1db3b
verified
just1nseo
commited on
Jul 24