Code

Tool fine-tuning support DPO#2479

Code

Open

August-murr wants to merge 3 commits intohuggingface:mainhuggingface/trl:mainfrom August-murr:tool_fine_tuning_supportAugust-murr/trl:tool_fine_tuning_supportCopy head branch name to clipboard

+43-3

Commits

Commits on Dec 14, 2024

• adding tool fine-tuning support for DPO

  August-murr

  committed
  7db18db

• precommit

  August-murr

  committed
  571a138

Commits on Dec 25, 2024

• adding test for DPOTrainer with tool usage

  August-murr

  committed
  dc19849