XMasterrrr
Joined 7 years ago
Karma
209
Submissions
31
Member since
Jan 1
Recent submissions
Comment · 1 year ago
Hey HN,
I've been neck-deep in AI and LLMs for a while now, and I kept running into the same problem: every learning resource out there for LLMs either tries to teach you all of deep learning from scratch, or throws you into a sea of random “awesome-LLM” repos, hoping you can connect the dots yourself.
So, I wrote up the roadmap I wish existed a year ago: how to actually learn LLMs and build real things, with none of the bloat. It's geared towards folks with a CS (or practical programming) background who want to skip the endless ML prerequisites and get their hands dirty. The approach:
- Concepts first, then phases, then resources/tools - Each phase has concrete projects (build an autograd engine, write a mini-GPT, fine-tune with LoRA, etc) - The goal is to get you actually building and shipping, not just watching lectures
Hope you guys find it useful.
-Ahmad
Comment · 1 year ago
What's your workflow like? I use AI Chat. I load Qwen2.5-1.5B-Instruct with llama.cpp server, fully offloaded to the CPU, and then I config AI Chat to connect to the llama.cpp endpoint.
Comment · 1 year ago
I think I know what he means. I use AI Chat. I load Qwen2.5-1.5B-Instruct with llama.cpp server, fully offloaded to the CPU, and then I config AI Chat to connect to the llama.cpp endpoint.
Checkout the demo they have below
Comment · 2 years ago
Hey guys, If you remember, I shared my first blogpost here a couple of weeks ago Serving AI From The Basement (https://ahmadosman.com/blog/basement-ai-resident/serving-ai-...) and there was a great and lively discussion thread (https://news.ycombinator.com/item?id=41481852) with a lot of good input and questions.
This is my second blogpost, and in this one: SWE Agentic Framework – think of it as the puppet master for coders plus Replit's next nemesis. MoEs – imagine a team of AI experts, each shouting answers when it's their topic. Quantizations & Mixed Precision – turning AI from gourmet to fast food without losing the flavor. Batch Inference – AKA AI's quiz night, answering all questions at once. LLM Architectures – blueprints for our chatty AI friends. vLLM and Tensor Parallelism – or the thing that makes big AI models run lean. DeepSeek v2.5 – our open weights savior. Embedding Models – translating human words into AI-understandable numbers. Speculative Decoding – or AI's attempt at mind-reading, guessing your sentences before you finish them.
In the next blogpost I plan on addressing the main pain points of the hardware build and following up on the most-asked questions I received on the first one. I apologize for taking so long to get that out there, but it is taking me more than I expected to properly cover everything I want.
Please let me know if you have any comments or questions, and always feel free to reach out either here or via the social links on my website.
Comment · 2 years ago
You've got a much stronger heart than me man
Comment · 2 years ago
Most outlets rely on 120v 15amp breakers here in the US, only washer/dryer/kitchenware require the higher end 240v breakers
Comment · 2 years ago
Yup, that's exactly what I had installed.
Comment · 2 years ago
Yeah, you get it. I have two PDUs with NEMA L6-30P plugin, and two NEMA L6-30R outlet. Each outlet is connected to it's dedicated 30A 240v circuit (which gives you a total of 60A, or 6000w).
Cooling is its own story... Man, figuring out this process was hella of a journey
Comment · 2 years ago
If that is true and OP is not just confused, he should sue his landlord, and I am not even kidding!!!
Comment · 2 years ago
What kind of a dryer? Because that cannot be right. Dryers require a 30amp 240volt dedicated breakers by code in most counties in most states nowadays.
Blog: https://www.ahmadosman.com
X/Twitter: https://x.com/TheAhmadOsman
GitHub: https://github.com/TheAhmadOsman/
LinkedIn: https://www.linkedin.com/in/TheAhmadOsman/
Email: me - at ~ ahmadosman.com