sfulay
/

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

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-magpi-reward-scale-1 / model-00002-of-00003.safetensors

Commit History

Training in progress, step 352

34aed1b
verified

sfulay commited on Aug 14, 2024

Training in progress, step 300

4748676
verified

sfulay commited on Aug 14, 2024

Training in progress, step 200

7165d2a
verified

sfulay commited on Aug 14, 2024