sfulay
/

zephyr-7b-dpo-full-gpt_consistent-reward-scale-1

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-gpt_consistent-reward-scale-1 / model-00003-of-00003.safetensors

Commit History

Training in progress, step 300

92bb885
verified

sfulay commited on Aug 28, 2024

Training in progress, step 200

775b078
verified

sfulay commited on Aug 28, 2024