Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
JayHyeon
/
pythia-2.8b-rDPO_5e-7_1.0vpo_constant-1ep_0.3label_smoothing
like
0
Text Generation
Transformers
TensorBoard
Safetensors
trl-lib/ultrafeedback_binarized
gpt_neox
Generated from Trainer
trl
dpo
conversational
text-generation-inference
arxiv:
2305.18290
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
Deploy
Use this model
main
pythia-2.8b-rDPO_5e-7_1.0vpo_constant-1ep_0.3label_smoothing
/
runs
19.8 kB
1 contributor
History:
1 commit
JayHyeon
Training in progress, step 970
721e795
verified
4 months ago
Aug05_20-50-53_01933a260f36
Training in progress, step 970
4 months ago