Comment on: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
Paper plates of software development.
Read more →Paper plates of software development.
Read more →Some of the coding-specific fine-tunes were really impressive boosts. Qwen2.5-3B-Instruct is also available [0] -- if it's not too much to ask, I'd be curious how more general models stack up in your benchmark? [0] - https://huggingface.co/Qwen/Qwen2.5-3B-Instruct
Read more →Setting up good book publishing pipelines with version control + CI/CD might sounds simple, but I don't think it's trivial. One of the best examples of this that I've ever seen is The Sourdough Framework [0] -- really impressed with the way that versioning and publishing is…
Read more →If the phone had broken comms, how did you get the code onto the phone to run?
Read more →This is very cool! If you're looking for a good test suite, I wonder if you might be able to adapt any of the tests available in XMage? They have a pretty extensive test suite (such as for copy effects [0]) and if you point your agent at their code, I wonder how many could be…
Read more →Oh cool! I've been doing similar experiments lately (using ViT's) to do card recognition, and so far it's been working really well for me. If you want to compare notes, I've open-sourced my code / weights [0] and written some blogs about how mine works [1]. I'd love to see if we…
Read more →Thank you! If you want to test out my tool, here's a link to the web version that is built for scanning in lists of cards: https://hanclinto.github.io/CollectorVision/ It's still super rough (doesn't support foil-toggling yet, still some issues with double-sided cards, crashing…
Read more →Thank you -- I appreciate that. :)
Read more →it seems i either take them to a shop and get lowballed, or spend hours meticulously researching each card and then figuring out how to sell it for what it’s worth. Well if you want to use the scanner for something useful, you can run the web version here:…
Read more →I resonate with this blog post a lot. I think there is something to be said for monetizing ones' hobbies, but I've recently been taking some forays into this world of "build something amazing and give it away for free" as well. I recently took a very big experimental plunge in…
Read more →It's not just about web search though -- there's another element too. I go to Grok to find things I have failed to find with web search. I agree with GP -- if I want sourced commentary on current events, Grok is my go-to above the other models. For whatever reason, its search…
Read more →This is seriously impressive!! What are you planning on doing with this? Where should I follow along?
Read more →This sounds delightful and wholesome. :D I think it's easy to lose sight of these pockets of mundane goodness, and I appreciate you highlighting them.
Read more →Bad URL, but this YouTube clip works for me: https://www.youtube.com/watch?v=5usXhX0zaO4
Read more →Microsoft releases a new open-weight model that tops the MTEB leaderboard for the largest model (27b), but also includes smaller models that are top of their respect "weight" classes (hah!) -- 0.6b (embedding size 1024) and 270m (embedding size 640). All have best-in-class…
Read more →Relevant XKCD "what if?" [0] is relevant. [0] - https://what-if.xkcd.com/32/
Read more →"The agent doesn't need a real filesystem; it just needs the illusion of one. Our documentation was already indexed, chunked, and stored in a Chroma database to power our search, so we built ChromaFs: a virtual filesystem that intercepts UNIX commands and translates them into…
Read more →Submitted by the author two days ago [0], but resubmitting here so that it doesn't violate the self-promotion rule. 0 - https://news.ycombinator.com/item?id=47524901
Read more →Full writeup by the Australian man who successfully created a custom mRNA vaccine for his dog's cancer
Read more →Yeah, but it can be a bit of a tight squeeze if you don't have at least 24gb (preferably 32gb+) of memory. Especially if you want other apps to run at the same time, I think it's safer to stick with something more like 9b. You can see a table with quantized sizes here [0] --…
Read more →