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
517a830
zephyr-7b-dpo-qlora-pairrm
/
adapter_model.safetensors
Commit History
Training in progress, step 700
517a830
verified
shenxq
commited on
Mar 18
Training in progress, step 600
ddeeaad
verified
shenxq
commited on
Mar 18
Training in progress, step 500
5f7d11c
verified
shenxq
commited on
Mar 18
Training in progress, step 400
2ff7a67
verified
shenxq
commited on
Mar 18
Training in progress, step 300
70a6103
verified
shenxq
commited on
Mar 18
Training in progress, step 200
966a90f
verified
shenxq
commited on
Mar 18
Training in progress, step 100
b2e7f86
verified
shenxq
commited on
Mar 18