Rare find

Llama4Micro. An AI model that runs on a tiny computer chip instead of a big server.

github.com/maxbbraun/llama4micro

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

December 2023

Cleaner way to specify the custom linker script Dec 8
Clarify that we're not using the smallest model Dec 4

November 2023

Highlight inference location Nov 28
Fix variable name typo Nov 28
Merge pull request #7 from maxbbraun/camera-input Nov 21
Remove unused intermediate file Nov 21
Move TPU context to narrower scope Nov 21
Freeing up memory from TPU doens't seem to work Nov 21
No objects log is no error Nov 21
Implement non-maximum suppression Nov 21
Switch to YOLOv5 for object detection Nov 20
Move models dir and include them in the repo Nov 20
Add ultralytics/yolov5 submodule Nov 20
Merge branch 'main' into camera-input Nov 19
Code cleanup Nov 19
Add image classification (on TPU) to use in prompt Nov 19
Adjust memory map for adding camera/TPU inference Nov 19
Clarify that Llama isn't running on the TPU Nov 19
Code cleanup Nov 17
Remove the need for a forked coralmicro Nov 17