fastai/course22

TensorFlow is Google's open-source, end-to-end platform for machine learning, hosted at tensorflow/tensorflow under the Apache-2.0 license. It was originally built within Google Brain's Machine Intelligence team for ML and neural network research, and today it ships stable Python and C++ APIs alongside GPU, CPU-only, and Docker install paths. The README positions it as covering both research work and shipping ML-powered applications.

Hugging Face Transformers (huggingface/transformers) is a Python library that centralizes model definitions for text, computer vision, audio, video, and multimodal machine learning, covering both inference and training. The README describes it as a pivot point compatible with training frameworks such as Axolotl, DeepSpeed, and PyTorch-Lightning, and inference engines such as vLLM, SGLang, and TGI, with more than 1M+ model checkpoints listed on the Hugging Face Hub.

PyTorch is an open-source Python package hosted at pytorch/pytorch on GitHub, built around two core capabilities: NumPy-like Tensor computation with GPU acceleration, and deep neural networks built through a tape-based autograd system. Its components include torch.nn for network layers, torch.jit for compiling models into TorchScript, and torch.multiprocessing for sharing Tensors across processes, with build support for CUDA, AMD ROCm, and Intel GPU backends documented in the README.

LLMs-from-scratch is Sebastian Raschka's GitHub companion to the Manning book Build a Large Language Model (From Scratch), ISBN 9781633437166. It walks through building, pretraining, and finetuning a GPT-style model in PyTorch across seven chapters and five appendices, plus a growing set of bonus notebooks covering newer open architectures.