sfulay
/

zephyr-7b-dpo-full-prometheus_consistent-reward-scale-1-rpo

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-prometheus_consistent-reward-scale-1-rpo / tokenizer.json

sfulay's picture

Training in progress, step 100

d1dca68 verified about 2 months ago

history contribute delete

1.8 MB

File too large to display, you can check the raw version instead.