sfulay
/

zephyr-7b-dpo-full-gpt_consistent-reward-scale-05

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-gpt_consistent-reward-scale-05 / model-00001-of-00003.safetensors

Commit History

Training in progress, step 100

251193f
verified

sfulay commited on Sep 3, 2024

Training in progress, step 100

4574324
verified

sfulay commited on Sep 3, 2024