Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
taicheng
/
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
8d629f6
zephyr-7b-dpo-qlora
/
runs
/
Sep12_19-06-53_qa-a100-005.crc.nd.edu
1 contributor
History:
1 commit
taicheng
Training in progress, step 100
8d629f6
verified
6 months ago
events.out.tfevents.1726182972.qa-a100-005.crc.nd.edu.304505.0
14.4 kB
LFS
Training in progress, step 100
6 months ago