News for hackers. Stuff that matters.

rojasdiego

Re:Ask HN: What are you working on (August 2024)? on Sunday August 25, 2024 @01:09AM (#41344559)
Is there a place where one can get familiar with your work on this?
Re:Nvidia RTX 5880 Ada 48GB Professional GPU Launched on Sunday January 07, 2024 @08:39PM (#38907270)
I’m confused about the RTX Ada 5000-6000 line-up. It seems they compare poorly to much cheaper GPUs such as an RTX 4090 (not taking into account VRAM) and I figure if a company wanted to scale out nodes they’d go for A100/H100 instead. What makes them attractive for companies?

Show HN: Train Your Own Language Model on Your Favourite Programming Language

https://github.com/rojas-diego/gopilot

In the context of the Deep Learning class at Tsinghua University, my teammates and I have trained our own (tiny) LLM on Go code using the `go/scanner` tokens as the tokenizer!If you're ever looking to train a single-GPU Language Model over the weekend on your favorite Programming Language, feel free to use our code and VSCode Extension.

( Read More... | no comments | on HN )