8000 GitHub - dnbt777/ml: ML from scratch in Jax
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

dnbt777/ml

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LEARN BY BUILDING: ML from scratch in Jax

in this repo I train my skills in ML by practicing implementing experiments in jax (from scratch, except the backwards pass), and optimizing them

Jax is (basically) numpy but with autograd. This lets me focus on getting good at implementation/training details without tediously implementing backprop by hand

I am doing this in a community on X called "LEARN BY BUILDING" where we build projects as a way to learn tech stuff: programming, robotics, etc. If you have something you want to learn, join, come up with a project, and post whenever you make progress!

alt text

Projects in progress

Use GRPO to survive a 3-body physics simulation with rockets (status: env implemented, GRPO implemented, but training needs refining)

Double deep Q net that plays 6D snake (status: 2D version completed, needs opengl renderer, needs upgrade from regular DQN to double DQN)

Llama 3.2 Vision 11B Inference (status: forward pass needs debugging)

projects so far

Train a small (19.2M) transformer on the dictionary

image

Train an RNN/LSTM on my x posts

alt text

Train a CNN on MNIST

  • custom CNN with skip connections on MNIST

alt text

Train an MLP on MNIST

goal

become very fast at replicating papers and complex experiments/architectures milestones:

  • replicate 1 paper per 2 months
  • replcate 1 paper every month
  • replicate 1 paper every 2 weeks
  • replicate 1 paper every week
  • replicate 2 papers a week
  • 4
  • 7
  • replicate 2 papers a day

(here, 'paper' means a model, or a custom experiment, or a random paper. this is not a super concrete metric bc of differences in paper difficulties, but it suffices)

About

ML from scratch in Jax

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0