epistoteles / TensorHue
TensorHue is a Python library that allows you to visualize tensors right in your console, making understanding and debugging tensor contents easier.
☆102Updated last week
Related projects: ⓘ
- ☆137Updated last month
- Universal Tensor Operations in Einstein-Inspired Notation for Python.☆316Updated last month
- Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).☆126Updated this week
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆115Updated last month
- ☆288Updated 2 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆82Updated 3 weeks ago
- Scalable neural net training via automatic normalization in the modular norm.☆108Updated last month
- Implementation of Diffusion Transformer (DiT) in JAX☆246Updated 3 months ago
- TensorDict is a pytorch dedicated tensor container.☆808Updated this week
- Memory mapped numpy arrays of varying shapes☆277Updated 3 months ago
- ☆124Updated 7 months ago
- Helpful tools and examples for working with flex-attention☆341Updated last month
- Transform datasets at scale. Optimize datasets for fast AI model training.☆318Updated this week
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- The AdEMAMix Optimizer: Better, Faster, Older.☆132Updated last week
- Annotated version of the Mamba paper☆445Updated 6 months ago
- For optimization algorithm research and development.☆240Updated last week
- 94% on CIFAR-10 in 3.09 seconds 💨 96% in 27 seconds☆127Updated last month
- Install PyTorch distributions with computation backend auto-detection☆216Updated last year
- Highly commented implementations of Transformers in PyTorch☆126Updated last year
- ☆192Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆452Updated last week
- Code release for "Dropout Reduces Underfitting"☆311Updated last year
- The boundary of neural network trainability is fractal☆155Updated 7 months ago
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆161Updated this week
- WIP☆76Updated last month
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆199Updated last year
- ☆180Updated 2 months ago
- GPT-2 (124M) quality in 5B tokens☆227Updated last week
- A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to fac…☆213Updated this week