One think I didn't see mentioned in the post- maybe I missed it- how large was the data? How many samples did you use to pretrain and post-train
4,908 karma · joined March 25, 2015
GitHub: https://github.com/jasonjmcghee
One think I didn't see mentioned in the post- maybe I missed it- how large was the data? How many samples did you use to pretrain and post-train
Why is it a blocking issue?
I feel like this is very aligned with the goals of rust-gpu.
Information can only be compressed so much
It's important to retain the what why and how as a team to the degree that development can be efficient, extensible, and maintainable. (And ideally a good devx)
Needing to manually touch every line of code is not scalable.
This was true 10 years ago. It's still true today.
So you can just, move up.
As it's 9 months old and they just had a major model release
"Use a black background and this hideously wide font!"
I expected $10 maybe $20. I think $40 is too far outside of impulse / nostalgia purchase.
Some person recognized a problem they wanted solved and put a bunch of effort into creating a unique solution.
I love this stuff.
This post is perfect for HN.
(Erdős problem 90)
So I'm guessing it came from representing the additional dimension
Commits also look like it’s this year only?
With dflash-mlx library, with dflash disabled 3.6-35b-a3b mlx model I'm getting ~60 t/s on low power and >100 t/s on high power.
Compared with previous message being official qwen huggingface release (non-mlx) using lm studio.
With no speculative decoding, using high power mode, I get 80 t/s on 35B A3B - and it gets hot and spins up. On low power mode I get 38 t/s - no fans, cool to warm laptop.
If you currently don't use speculative decoding and you start using it, it can nearly offset the difference between high and low power, and it's night and day experience.
I almost always keep my laptop on low power mode.
If you have a subscription it's a different pool of usage.
I think many people go through the very popular https://raytracing.github.io/
There was a big influx of this when Sebastian Lague did his video series on building a ray tracer.
Others just draw the SVG path or wiggle/bounce a bit.
If I were the creator here I might differentiate this into two buckets: custom animation or not. And then allow the generic animations to be applied to any of them.