ondevicellm
/

tinyllama_moe_dpo_ultrachat_v2_epochs3

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

tinyllama_moe_dpo_ultrachat_v2_epochs3 / runs

1 contributor

History: 22 commits

hushell's picture

Training in progress, step 2600

43f05ab verified 10 months ago

Jan22_17-48-19_main1
Training in progress, step 2600 10 months ago