Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
sfulay
/
zephyr-7b-dpo-full-ultrabin-3-avg-logprob-lr-same
like
0
Safetensors
mistral
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
zephyr-7b-dpo-full-ultrabin-3-avg-logprob-lr-same
/
tokenizer.json
Commit History
Training in progress, step 100
24f57e1
verified
sfulay
commited on
Aug 19, 2024