Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jiangjun0105woven
/
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
main
zephyr-7b-dpo-qlora
Commit History
End of training
cd1a359
verified
jiangjun0105woven
commited on
22 days ago
Model save
aa9c5c8
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 637
635e5c2
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 600
f1a6188
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 500
cca2992
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 400
d0c6079
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 300
462bb24
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 200
4474e4a
verified
jiangjun0105woven
commited on
22 days ago
Training in progress, step 100
0a06490
verified
jiangjun0105woven
commited on
22 days ago
initial commit
67080f5
verified
jiangjun0105woven
commited on
29 days ago