Alvaro Bartolome

ML engineer at Hugging Face working on alignment handbooks, TRL, and post-training tooling.

Cite

Notes

Only stored in your browser.

Attribution

1tool contribs

Tool contributions

Argilla

A high-quality DPO derivative of LDJnr's Capybara, with chosen/rejected pairs synthesized and rated using Argilla's distilabel pipeline.

Currently at

engineer · infra