✨Rodmar パブロ✨

14.6K posts

✨Rodmar パブロ✨ banner
✨Rodmar パブロ✨

✨Rodmar パブロ✨

@rodmarkun

I like computers | software engineer

🇪🇸 شامل ہوئے Aralık 2012
737 فالونگ2.7K فالوورز
پن کیا گیا ٹویٹ
✨Rodmar パブロ✨
✨Rodmar パブロ✨@rodmarkun·
Hey guys! SmolML is now out! A small Machine Learning library I made completely from scratch (no external libraries) for educational purposes. I've recently added comprehensive guides explaining every concept from the ground up – from automatic differentiation to backpropagation, n-dimensional arrays and tree-based algorithms. This isn't meant at all to replace production libraries (it's purposely slow since it's pure Python!), but rather to serve as a learning resource for anyone wanting to understand how ML actually works beneath all the abstractions. If you're learning ML or just curious about the inner workings of libraries like Scikit-learn or PyTorch, I'd love to hear your thoughts or feedback! :)
✨Rodmar パブロ✨ tweet media✨Rodmar パブロ✨ tweet media✨Rodmar パブロ✨ tweet media
English
17
110
749
48.2K
✨Rodmar パブロ✨
type shi I watch while spinning 3 claude instances to solve jira tickets
✨Rodmar パブロ✨ tweet media
English
1
0
20
337
✨Rodmar パブロ✨ ری ٹویٹ کیا
Sudo su
Sudo su@sudoingX·
this guy has 29 models on huggingface at page 2 ranking. no lab behind him. no sponsorship. $2,000 from his own pocket on GPU rentals. he compressed GLM-4.7 to run on a MacBook and quantized Nemotron Super the week it dropped. all public. all free. nvidia is a trillion dollar company with hundreds of teams but they are not the ones quantizing models middle of the night and pushing them out before sunrise. if nvidia stopped tomorrow their employees stop working. people like @0xSero would not. that is the difference between a paycheck and a mission. @NVIDIAAI you talk about making AI accessible. the people actually doing it are right here. 29 models deep burning their own compute with no ask except more hardware to keep going. you do not need to build another program. just look at who is already building for you. one GPU to this man would produce more public value than a hundred internal sprints. i am not asking for charity. i am asking you to invest in someone who already proved it.
Sudo su tweet media
0xSero@0xSero

Putting out a wish to the universe. I need more compute, if I can get more I will make sure every machine from a small phone to a bootstrapped RTX 3090 node can run frontier intelligence fast with minimal intelligence loss. I have hit page 2 of huggingface, released 3 model family compressions and got GLM-4.7 on a MacBook huggingface.co/0xsero My beast just isn’t enough and I already spent 2k usd on renting GPUs on top of credits provided by Prime intellect and Hotaisle. ——— If you believe in what I do help me get this to Nvidia, maybe they will bless me with the pewter to keep making local AI more accessible 🙏

English
180
1.1K
12.5K
761.1K
✨Rodmar パブロ✨
✨Rodmar パブロ✨@rodmarkun·
Did a small local anime server tool powered by Hermes Agent (@NousResearch). You can: - fully sync your anime list - download torrents from different sources - add tracking & scheduled downloads - auto-manage disk usage - serve to any device within your local wifi and more!
English
3
64
1.1K
45.6K
✨Rodmar パブロ✨
✨Rodmar パブロ✨@rodmarkun·
@Teknium been doing some cool stuff, will post about it today! didn't know you were having a hackathon as well 👀
English
1
0
1
32
Teknium 🪽
Teknium 🪽@Teknium·
@rodmarkun Showing off what cool things you have been able to do with hermes and participating in our hackathon, or making video/blog tutorials on what kinds of things you can do/setup guides etc!
English
1
0
1
108
Teknium 🪽
Teknium 🪽@Teknium·
If you're wondering why there's only 100 or so commits today instead of 500 or so, I'm working on a clean refactor of providers:models because all these new providers are making a mess of the codebase x] Patience on a few other things plz 🙏
Nous Research@NousResearch

Meet Hermes Agent, the open source agent that grows with you. Hermes Agent remembers what it learns and gets more capable over time, with a multi-level memory system and persistent dedicated machine access.

English
25
6
239
15.6K
✨Rodmar パブロ✨ ری ٹویٹ کیا
Ihtesham Ali
Ihtesham Ali@ihtesham2005·
🚨BREAKING: NousResearch just dropped a fully open-source AI agent that lives on your server forever. It's called Hermes Agent and it's the personal AI assistant that actually grows the longer it runs. - Telegram, Discord, Slack, WhatsApp + CLI from one gateway - Persistent memory across sessions - Writes its own skill documents when it solves hard problems - Built-in cron scheduler for automated tasks - Spawns isolated subagents for parallel workstreams - Runs on any model: Claude, GPT, local VLLM, OpenRouter 200+ models 100% Opensource. MIT License.
Ihtesham Ali tweet media
English
26
73
469
37K
✰λster✰
✰λster✰@4ster_light·
@rodmarkun Hey bro que tal, justo hoy tengo los regionales de la Hackathon Ada-Byron jejeje
Español
1
0
3
51
wukko
wukko@uwukko·
well hello there
wukko tweet media
English
100
26
2.2K
87.2K
Nithin
Nithin@nithin_twts·
@rodmarkun Dude I drew inspiration for my portfolio page from yours! So cool, keep going at it!
English
1
0
1
72
✨Rodmar パブロ✨ ری ٹویٹ کیا
Max Mynter
Max Mynter@MaxMynter·
Great blogpost from a colleague of mine. Really interesting stuff mistral.ai/news/debugging…
Max Mynter tweet media
English
3
76
563
55.5K
✨Rodmar パブロ✨
✨Rodmar パブロ✨@rodmarkun·
@Aryvyo I've been looking into bsky and even tho there's way less people I find that to be even better much less noise and more signal than over here if you're into niche stuff
English
0
0
2
14
Aryas
Aryas@Aryvyo·
@rodmarkun The niche space is dead. Long live the sloppy amalgamation of every culture.
English
1
0
5
59
Aryas
Aryas@Aryvyo·
It’s crazy you can really tell nikita thinks he’s some visionary or some insane esoteric thinker who will bring about a new era of social media because he can maximize brainrot user retention (like any other social media app)
English
2
0
18
583