Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-v1-i2
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
cfd6c79
zephyr-7b-gpo-v1-i2
/
runs
1 contributor
History:
13 commits
lole25
Training in progress, step 1800
cfd6c79
verified
5 months ago
May11_20-10-24_gpu4-119-4
Training in progress, step 500
5 months ago
May11_20-54-51_gpu4-119-5
Training in progress, step 100
5 months ago
May11_22-24-47_gpu4-119-5
Training in progress, step 1800
5 months ago