fl0wbar's Stars
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
huggingface/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
huggingface/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
jax-ml/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
huggingface/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
huggingface/accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
crowsonkb/k-diffusion
Karras et al. (2022) diffusion models for PyTorch
KellerJordan/modded-nanogpt
NanoGPT (124M) in 3 minutes
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
tensorflow/compression
Data compression in TensorFlow
KellerJordan/cifar10-airbench
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
HomebrewML/HeavyBall
Efficient optimizers
lixilinx/psgd_torch
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
paradigms-of-intelligence/cubff
znah/zff
8-bit computational substrates
evanatyourservice/psgd_jax
Implementation of PSGD optimizer in JAX
lixilinx/Fully-Trainable-SSM
A fully trainable state space model (SSM)