tinygrad
NNfSiX
tinygrad | NNfSiX | |
---|---|---|
58 | 46 | |
17,800 | 1,359 | |
- | - | |
9.7 | 0.0 | |
10 months ago | 8 months ago | |
Python | C++ | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tinygrad
- tinygrad: extreme simplicity, easiest framework to add new accelerators to
-
GGML – AI at the Edge
Might be a silly question but is GGML a similar/competing library to George Hotz's tinygrad [0]?
[0] https://github.com/geohot/tinygrad
-
Render neural network into CUDA/HIP code
at first glance i thought may its like tinygrad. but looks has many ops than that tiny grad but most maps to underlying hardware provided ops?
i wonder how well tinygrad's apporach will work out, ops fusion sounds easy, just a walk a graph, pattern match it and lower to hardware provided ops?
Anyway if anyone wants to understand the philosophy behind tinygrad, this file is great start https://github.com/geohot/tinygrad/blob/master/docs/abstract...
-
llama.cpp now officially supports GPU acceleration.
There are currently at least 3 ways to run llama on m1 with GPU acceleration. - mlc-llm (pre-built, only 1 model has been ported) - tinygrad (very memory efficient, not that easy to integrate into other projects) - llama-mps (original llama codebase + llama adapter support)
- George Hotz building an AMD competitor to Nvidia.
-
George Hotz ROCm adventures
Hopefully we will see now full support with AMD hardware on https://github.com/geohot/tinygrad. You can read more about it on https://tinygrad.org/
-
The Coming of Local LLMs
tinygrad
https://github.com/geohot/tinygrad/tree/master/accel/ane
But I have not tested it on Linux since Asahi has not yet added support.
llama.cpp runs at 18ms per token (7B) and 200ms per token (65B) without quantization.
- Everything we know about Apple's Neural Engine
- Everything we know about the Apple Neural Engine (ANE)
- How 'Open' Is OpenAI, Really?
NNfSiX
-
Are there any books I should read to learn machine learning from scratch?
I've been rather enjoying "Neural Networks from Scratch" (https://nnfs.io/)
-
Ask HN: Those learning about neural networks, what do you find most difficult?
I haven't gotten super deep into it yet, but https://nnfs.io/ has been good in my opinion. The book slowly replaces written and explained code with numpy equivalents to keep the examples fast. Plus the accompanying animations are also useful. I would be curious what others think on it too.
- Gutes Einführungsbuch zu KI
- [Deep Learning] Neural Networks from Scratch in Python
- What do I get a programming obsessed high school boy for his birthday? I actually need advice
-
GPT in 60 Lines of NumPy
For those curious to writing "gradient descent with respect to some loss function" starting from an empty .py file (and a numpy import, sure), can't recommend enough Harrison "sentdex" Kinsley's videos/book Neural Networks from Scratch in Python [1].
[1] https://youtu.be/Wo5dMEP_BbI?list=PLQVvvaa0QuDcjD5BAw2DxE6OF... https://nnfs.io
-
Ask HN: What are the foundational texts for learning about AI/ML/NN?
Not sure if foundational (quite a tall order in such a fast-moving field), but for sure a nice introduction into neural networks, and even mathematics in general (because it's nice to see numbers in action beyond school-level algebra):
Harrison Kinsley, Daniel Kukiela, Neural Networks from Scratch, https://nnfs.io, https://www.youtube.com/watch?v=Wo5dMEP_BbI&list=PLQVvvaa0Qu...
-
Ask HN: How to get back into AI?
Have you had a look at https://nnfs.io/ ? I bought the book and am gearing up to start working through it, I would be interested to know your thoughts. Generally I want to chart a personal curriculum from data engineer to practical application of modern AI to real business problems.
-
Programming an AI as a beginner
You can check out Neural Networks from Scratch in Python for an introduction to neural networks, which can be used for image classification. Please be forewarned that you'll need the mathematics necessary to read through this book - however, I'm assuming that since you've selected writing such an algorithm(s) in Python for your final school project that you're aware of such.
-
Moved to amd today and holy it's amazing
I am planning on working my way through Neural Networks From Scratch (https://nnfs.io/) in a few months just to build my understanding. After that I'm hoping to be able to figure out the best path for a couple of projects I have in mind.
What are some alternatives?
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
deeplearning-notes - Notes for Deep Learning Specialization Courses led by Andrew Ng.
llama.cpp - LLM inference in C/C++
ML-From-Scratch - Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
openpilot - openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for 250+ supported car makes and models.
micrograd - A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
llama - Inference code for Llama models
deepnet - Educational deep learning library in plain Numpy.
tensorflow_macos - TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.
minGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
ProjectOne - The project is to build a neural network from scratch. The motivation for this project is from nnfs.io a website build by @Sentdex. Nnfs.io is actually meant for a book that teaches the fundamentals of neural network and help us to build our own network. Let's build a new neural network where we can learn the fundamentals and make a great hands-on work space for aspiring machine learning engineers and the GitHub community