Add ORPO within `README.md` files

huggingface / alignment-handbook

Robust recipes to align language models with human and AI preferences

https://huggingface.co/HuggingFaceH4

Apache License 2.0

4.53k stars 393 forks source link

Add ORPO within `README.md` files #154

Closed alvarobartt closed 5 months ago

alvarobartt commented 5 months ago

Description

This PR adds the ORPO fine-tuning technique among the existing README.md files where the available techniques are mentioned, as well as adding https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 within the "News" section.

Additionally, this PR also fixes a small typo in the ModelArguments from adatpers to adapters.

Thanks @nisten for realising that the docs were missing https://github.com/huggingface/alignment-handbook/pull/143#issuecomment-2051497473

HuggingFaceDocBuilderDev commented 5 months ago

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.