The Weekly Kaitchup #10

Oct 13, 2023

Zephyr 7B - LongLLMLingua - gte-tiny - Mistral 7B paper - OpenWebMath

2 Comments

Oct 16, 2023Liked by Benjamin Marie

Is there a GitHub repo for doing DPO?

Expand full comment

Oct 16, 2023Author

DPO is possible with HF's TRL:

https://huggingface.co/docs/trl/main/en/dpo_trainer

Expand full comment

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts