EllieS
/

zephyr-7b-dpo-lora-pubmedqa-selfgen-old

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-lora-pubmedqa-selfgen-old / tokenizer_config.json

Commit History

Training in progress, step 1000

81b37df
verified

EllieS commited on Feb 20