bpesquet / pyfit
A minimalist neural networks library built on a tiny autograd engine
☆16Updated 3 months ago
Related projects: ⓘ
- ☆97Updated this week
- A pure-functional implementation of a machine learning transformer model in Python/JAX☆173Updated 2 years ago
- Module 0 - Fundamentals☆95Updated 3 weeks ago
- ML/DL Math and Method notes☆56Updated 9 months ago
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆41Updated 3 months ago
- ☆108Updated last year
- An interactive exploration of Transformer programming.☆243Updated 10 months ago
- Implements the Tsetlin Machine, Coalesced Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetli…☆120Updated 3 weeks ago
- Resources from the EleutherAI Math Reading Group☆50Updated 2 months ago
- ☆46Updated 2 months ago
- Multidimensional indexing for tensors☆108Updated last year
- ☆18Updated 5 months ago
- This is a port of Mistral-7B model in JAX☆29Updated 2 months ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆42Updated 3 years ago
- Highly commented implementations of Transformers in PyTorch☆126Updated last year
- Teaching transformers to play chess☆39Updated last month
- ☆56Updated 2 years ago
- Jax like function transformation engine but micro, microjax☆24Updated 3 weeks ago
- Neural Networks for JAX☆82Updated 2 months ago
- ☆137Updated last month
- Scripts to prep PC for development use after OS installs☆37Updated 3 weeks ago
- ☆24Updated last year
- This code repository contains the code used for my "Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch" blog po…☆84Updated last year
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆58Updated 2 years ago
- ☆17Updated 4 months ago
- Implementation of Stable Diffusion from scratch [WORK IN PROGRESS]☆21Updated last year
- ☆325Updated 11 months ago
- A lightweight deep learning framework☆32Updated 3 years ago
- The boundary of neural network trainability is fractal☆155Updated 7 months ago
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆132Updated 4 years ago
- Pre-train BERT from scratch, with HuggingFace. Accompanies the blog post: sidsite.com/posts/bert-from-scratch☆37Updated last year