course22p2
minGPT
| course22p2 | minGPT | |
|---|---|---|
| 6 | 35 | |
| 431 | 18,932 | |
| 2.6% | - | |
| 0.0 | 0.0 | |
| 11 days ago | 11 days ago | |
| Jupyter Notebook | Python | |
| Apache License 2.0 | 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.
course22p2
-
Ask HN: Daily practices for building AI/ML skills?
Practical Deep Learning for Coders: https://course.fast.ai/Lessons/part2.html
- Stanford A.I. Courses
-
A quick visual guide to what's actually happening when you generate an image with Stable Diffusion
To me the most important bit is that the diffusion loop turns a noisy latent into an image, does that iteratively, and uses "guidance" in the form of a prompt/controlnet image/etc to do it. The scheduler part, I felt, was needlessly complex for this short explainer, so I hand-wave it away. IF someone wants to dive in deeper, much deeper, they can go through the same thing I'm doing, which is this: https://course.fast.ai/Lessons/part2.html
- Practical Deep Learning for Coders - Part 2 overview
-
Courses for an AI beginner
They also recently released a course for more experienced students where they teach you to implement the Stable Diffusion algorithm from scratch.
-
From Deep Learning Foundations to Stable Diffusion (Part 2)
The full transcripts are available here in plain text form:
https://github.com/fastai/course22p2/tree/master/summaries
minGPT
- FLaNK AI Weekly for 29 April 2024
-
Ask HN: Daily practices for building AI/ML skills?
minGPT (Karpathy): https://github.com/karpathy/minGPT
Next, some foundational textbooks for general ML and deep learning:
-
[D] What are some examples of being clever with batching for training efficiency?
Language Model novice here. I was going through the README section of minGPT and read this line.
-
LLM Visualization: 3D interactive model of a GPT-style LLM network running inference.
The first network displayed with working weights is a tiny such network, which sorts a small list of the letters A, B, and C. This is the demo example model from Andrej Karpathy's minGPT implementation.
- LLM Visualization
- Learn Machine Learning
-
Facebook Prophet: library for generating forecasts from any time series data
Tried it once. Its promise is to take the dataset's seasonal trend into account, which makes sense for Facebook's original use case.
We ran it on such a dataset and found out that directly using https://github.com/karpathy/minGPT consistently gives a better result. So we ended up using the output of Prophet as an input feature to a neural network, but the result was not improved in any significant way.
-
Tokenization of numerical series
Sure, im trying to regenerate a bunch of complex numbers based on their absolute value. So im trying to embed these absolute values and then using gpt model(probably mini gpt) try to recover the original comples numbers. There is a certain connection between these complex numbers and their order which im not capable of explaining yet. Im hoping the model would be capable of recognizing certain sequences of these absolute values and match them with the desired complex counterparts (by training the model).
-
Anyone know of any articles on training a LLM from scratch on a single GPU?
minGPT (https://github.com/karpathy/minGPT)
-
Understanding LLMs(to the best of our knowledge)
Check out minGPT and nanoGPT from Karpathy, he puts out some of the best machine learning tutorials and teaching content.
What are some alternatives?
developer - the first library to let you embed a developer agent in your own app!
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
simpleaichat - Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
playground - Play with neural networks!
simpletransformers - Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
latentblending - Create butter-smooth transitions between prompts, powered by stable diffusion
Pytorch-Simple-Transformer - A simple transformer implementation without difficult syntax and extra bells and whistles.
machine-learning-specialization-andrew-ng - A collection of notes and implementations of machine learning algorithms from Andrew Ng's machine learning specialization.
nn-zero-to-hero - Neural Networks: Zero to Hero
stylegan2-projecting-images - Projecting images to latent space with StyleGAN2.
huggingface_hub - The official Python client for the Huggingface Hub.