Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
nnheui
/
pythia-1.4b-dpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
gpt_neox
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
pythia-1.4b-dpo-full
/
runs
/
Jul08_11-47-26_42dbe5cf9ed4
1 contributor
History:
2 commits
nnheui
End of training
d0ee6ee
verified
7 months ago
events.out.tfevents.1720439808.42dbe5cf9ed4.850226.0
Safe
5.34 kB
LFS
Model save
7 months ago
events.out.tfevents.1720440087.42dbe5cf9ed4.850226.1
Safe
970 Bytes
LFS
End of training
7 months ago