How to Train an AI Image Model on Yourself (coryzue.com)

Screenshot of coryzue.com: How to Train an AI Image Model on Yourself

First screen, captured 1 year ago.

Looks similar

Screenshot of seangoedecke.com: Should LLMs just treat text content as an image?

Should LLMs just treat text content as an image?(seangoedecke.com)

159 points by ingve 1 year ago | 94 comments

Screenshot of seangoedecke.com: What's the strongest AI model you can train on a laptop in five minutes?

What's the strongest AI model you can train on a laptop in five minutes?(seangoedecke.com)

476 points by ingve 1 year ago | 173 comments

Sean Goedecke's blog post on training the best small GPT-style model possible on a MacBook Pro in five minutes, landing on a ~1.8M-parameter transformer trained on TinyStories.

transformers tinystories language-models model-training

Screenshot of floydhub.ghost.io: Emil's Story as a Self-Taught AI Researcher (2020)

Emil's Story as a Self-Taught AI Researcher (2020)(floydhub.ghost.io)

81 points by eamag 1 year ago | 16 comments

Screenshot of minimaxir.com: LLMs can now identify public figures in images

LLMs can now identify public figures in images (minimaxir.com)

27 points by minimaxir 1 year ago | 2 comments

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

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.

music-generation midi transformers on-device-ml