nthakur
/

mistral-7b-instruct-v0.2-dpo-multilingual-mix-1st-apr-final

alignment-handbook

Generated from Trainer

Model card Files Files and versions

mistral-7b-instruct-v0.2-dpo-multilingual-mix-1st-apr-final / train_results.json

Commit History

Model save

f9e6f19
verified

nthakur commited on Apr 2, 2024