Search
Results
1 BIT IS ALL WE NEED: Binary Normalized Neural Networks
[2509.07025] 1 bit is all we need: binary normalized neural networks
One long sentence is all it takes to make LLMs misbehave • The Register
Bring your own brain? Why local LLMs are taking off • The Register
Beyond the Cloud: Why I’m Now Running Enterprise AI on My Laptop (Without Internet) | by Klaudi | Aug, 2025 | Medium
[https://medium.com/@klaudibregu/beyond-the-cloud-why-im-now-running-enterprise-ai-on-my-laptop-without-internet-16929a585328] - - public:mzimmerm
The Generative AI Con
The LLMentalist Effect: how chat-based Large Language Models replicate the mechanisms of a psychic's con
Every Reason Why I Hate AI and You Should Too
A Hitchhiker's Guide to the AI Bubble
Jan: Open source ChatGPT-alternative that runs 100% offline - Jan
(86) QwQ: Tiny Thinking Model That Tops DeepSeek R1 (Open Source) - YouTube
[https://www.youtube.com/watch?v=W5GmuOaUj3w] - - public:mzimmerm
Model which uses reinforcement learning.
Who needs GitHub Copilot when you can roll your own AI code assistant at home • The Register
Honey, I shrunk the LLM! A beginner's guide to quantization • The Register
The Best GPUs for Deep Learning in 2023 — An In-depth Analysis
BERT Transformers – How Do They Work? | Exxact Blog
[https://www.exxactcorp.com/blog/Deep-Learning/how-do-bert-transformers-work] - - public:mzimmerm
Excellent document about BERT transformers / models and their parameters: - L=number of layers. - H=size of the hidden layer = number of vectors for each word in the sentence. - A = Number of self-attention heads - Total parameters.
Introduction - Hugging Face NLP Course
[https://huggingface.co/learn/nlp-course/chapter1/1] - - public:mzimmerm
Natural Languge processing - full course.
How to train a new language model from scratch using Transformers and Tokenizers
[https://huggingface.co/blog/how-to-train] - - public:mzimmerm
Describes how to train a new language (desperanto) model.