pranftw / neograd
A deep learning framework created from scratch with Python and NumPy
☆234Updated last year
Related projects ⓘ
Alternatives and complementary repositories for neograd
- Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.☆105Updated 7 months ago
- Outlining techniques for improving the training performance of your PyTorch model without compromising its accuracy☆124Updated last year
- Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines☆195Updated 6 months ago
- From zero to hero CUDA for accelerating maths and machine learning on GPU.☆171Updated 4 months ago
- ☆37Updated 11 months ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆250Updated last year
- A really tiny autograd engine☆87Updated 7 months ago
- port of Andrjey Karpathy's llm.c to Mojo☆325Updated last month
- Autograd to GPT-2 completely from scratch☆107Updated 3 months ago
- The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX☆408Updated 7 months ago
- Highly commented implementations of Transformers in PyTorch☆129Updated last year
- A working machine learning framework in pure Mojo 🔥☆128Updated 7 months ago
- A Jax-based library for designing and training transformer models from scratch.☆276Updated 2 months ago
- A Machine Learning framework from scratch in Pure Mojo 🔥☆414Updated this week
- Implementation of Karpathy's micrograd in Mojo☆68Updated last year
- Website for Practical Deep Learning for Coders 2022☆47Updated 4 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆483Updated 3 weeks ago
- For optimization algorithm research and development.☆452Updated this week
- Notebooks for the "JAX in Action" book☆116Updated 5 months ago
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆338Updated this week
- 🤖 A PyTorch library of curated Transformer models and their composable components☆867Updated 7 months ago
- Tensors and dynamic Neural Networks in Mojo☆125Updated 4 months ago
- Recreating PyTorch from scratch (C/C++, CUDA, NCCL and Python, with multi-GPU support and automatic differentiation!)☆114Updated 5 months ago
- A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many different…☆271Updated 3 weeks ago
- deep learning with pytorch lightning☆0Updated 3 weeks ago
- The Tensor (or Array)☆411Updated 3 months ago
- IDE for PyTorch and its ecosystem☆383Updated 6 months ago
- ☆392Updated last month
- A pure NumPy implementation of Mamba.☆216Updated 4 months ago
- Build and train Neural Networks in Mojo☆207Updated 2 months ago