Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
shenxq
/
zephyr-7b-dpo-qlora-pairrm
like
0
PEFT
Safetensors
snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
b2e7f86
zephyr-7b-dpo-qlora-pairrm
Commit History
Training in progress, step 100
b2e7f86
verified
shenxq
commited on
Mar 18
initial commit
ada6e2b
verified
shenxq
commited on
Mar 18