Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jikaixuan
/
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
6366e7e
zephyr-7b-dpo-qlora
/
runs
1 contributor
History:
1 commit
jikaixuan
Training in progress, step 100
04ab470
verified
10 months ago
Jan13_16-49-44_uclaml03.cs.ucla.edu
Training in progress, step 100
10 months ago
Jan13_16-55-10_uclaml03.cs.ucla.edu
Training in progress, step 100
10 months ago