sfulay
/

zephyr-7b-dpo-full-prometheus-reward-scale-01

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-prometheus-reward-scale-01 / model-00001-of-00003.safetensors

Commit History

Training in progress, step 437

9ca7220
verified

sfulay commited on Aug 21, 2024

Training in progress, step 400

07ad681
verified

sfulay commited on Aug 20, 2024

Training in progress, step 300

155f7d9
verified

sfulay commited on Aug 20, 2024

Training in progress, step 200

14faf0d
verified

sfulay commited on Aug 20, 2024

Training in progress, step 100

406fa7e
verified

sfulay commited on Aug 20, 2024