Fine-Tuning LLMs to 1.58bit(huggingface.co)

24 points by galeos 2 years ago | 1 comments

Fine-tuning Mistral 7B on Magic the Gathering Draft(generallyintelligent.substack.com)

324 points by dmakian 2 years ago | 89 comments

Substack post by David Hershey sharing tips, examples, and lessons from fine-tuning Mistral 7B to make Magic: The Gathering draft picks.

Fine-tuning LLMs is a waste of time(codinginterviewsmadesimple.substack.com)

156 points by j-wang 1 year ago | 65 comments

Show HN: I trained a 125M model to autocomplete piano on-device(simedw.com)

533 points by simedw 2 months ago | 110 comments

Blog post describing training a 125M-parameter transformer that autocompletes MIDI piano performances in real time on an iPhone, covering representation, data cleaning, and DPO.

Mistral 7B Fine-Tune Optimized(openpipe.ai)

203 points by tosh 2 years ago | 97 comments

When Fine-Tuning Makes Sense: A Developer's Guide(getkiln.ai)

138 points by scosman 1 year ago | 53 comments