Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ale-bay
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
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
d02fd4f
zephyr-7b-dpo-qlora
/
runs
1 contributor
History:
31 commits
ale-bay
Training in progress, step 1700
d02fd4f
verified
8 months ago
Mar07_10-30-46_ale-dpo-2-0-0
Training in progress, step 1700
8 months ago
Mar07_10-37-47_ale-dpo-1-0-0
Training in progress, step 1600
8 months ago