🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Inference code for Llama models

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

You like pytorch? You like micrograd? You love tinygrad! ❤️

The official Meta Llama 3 GitHub site

A high-throughput and memory-efficient inference and serving engine for LLMs

Code for the paper "Language Models are Unsupervised Multitask Learners"

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Ongoing research training transformer models at scale

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

structured outputs for llms

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Use commands in English to control Blender with OpenAI's GPT-4

An unnecessarily tiny implementation of GPT-2 in NumPy.

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

A library for mechanistic interpretability of GPT-style language models

GPS receiver from a raw antenna 🛰️