Rendered at 08:34:34 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
dannyw 3 hours ago [-]
Very cool project! Sounds like it was a fun challenge :)
I wonder when we'll start seeing clusters of ESP32-S3s... not sure how interconnects would go though, but I guess the interconnect wouldn't be the bottleneck anyway.
ReactiveJelly 2 hours ago [-]
Imagine a Beowulf cluster of those
chicken-stew 2 hours ago [-]
Would probably be better to demonstrate by exsmple how this approach is used to train on sensor data and then use it (as is hinted by the author) instead of acknowledging that the klingon poc is useless.
andai 2 hours ago [-]
Very cool project.
> Backpropagation (gradients derived by hand)
What does by hand mean in this context?
Also how did you write the readme? It's a curious blend of human and AI writing.
porridgeraisin 2 minutes ago [-]
The fact that by hand is emphasized so often and so often (see src/handgpt.h comments as well above backward()) makes me think it's AI.
Anyways, it looks like gradients derived by hand means they didn't use autograd. They have written out the expression for dL/dW themselves.
pavelai 4 hours ago [-]
This small Klingon speaking language model was trained completely on ESP32. The training took 2 days
Number of parameters: 319K
(Disclaimer) The models is tiny and is not a pocket chatbot. It mistakes and is not capable to support conversation, but that's not the goal of the project
The goals of the project is to bring training to edge devices and it worked out
How can one use it? By using solar panels such device could be turned into autonomous meteorological station
I wonder when we'll start seeing clusters of ESP32-S3s... not sure how interconnects would go though, but I guess the interconnect wouldn't be the bottleneck anyway.
> Backpropagation (gradients derived by hand)
What does by hand mean in this context?
Also how did you write the readme? It's a curious blend of human and AI writing.
Anyways, it looks like gradients derived by hand means they didn't use autograd. They have written out the expression for dL/dW themselves.
Number of parameters: 319K
(Disclaimer) The models is tiny and is not a pocket chatbot. It mistakes and is not capable to support conversation, but that's not the goal of the project
The goals of the project is to bring training to edge devices and it worked out
How can one use it? By using solar panels such device could be turned into autonomous meteorological station