Katayoon
/

DPO-ONLY-Zephyr-7B-3-iter-1

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

DPO-ONLY-Zephyr-7B-3-iter-1 / trainer_state.json

Commit History

Model save

10a5ab6
verified

Katayoon commited on Aug 1