Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
zephyr_0.1 – AI Model by chujiezheng | AlphaNeural AI
You can deploy this model and start earning money today!
chujiezheng
/
zephyr_0.1
like
0
transformers
tensorboard
safetensors
mistral
text-generation
conversational
en
2404.16792
apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
zephyr_0.1
The DPO-trained model from
alignment-handbook/zephyr-7b-sft-full
using 10% data of
HuggingFaceH4/ultrafeedback_binarized
, as in the "
Weak-to-Strong Extrapolation Expedites Alignment
" paper.
