Fully open reproduction of DeepSeek-R1

Smart commit messages

A realtime serving engine for Data-Intensive Generative AI Applications

High-performance, asynchronous Python HTTP client library designed for faster file transfers using concurrency, semaphores, and fault-tolerant features.

Instructify 📝 for easy Fine-Tuning preparation

An improved autograd engine that expands Andrej Karpathy's micrograd. Supports distributed tensors, enhanced operations, graph optimization, and visualization. Ideal for advanced machine learning c…

A stand-alone implementation of several NumPy dtype extensions used in machine learning.

The Multilayer Perceptron Language Model

The Tensor (or Array)

Efficient Triton Kernels for LLM Training

The n-gram Language Model

The Autograd Engine

LLM101n: Let's build a Storyteller

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

🤗 AutoTrain Advanced

Robust recipes to align language models with human and AI preferences

Presents comprehensive benchmarks of XLA-compatible pre-trained models in Keras.

so-vits-svc fork with realtime support, improved interface and more features.

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

Home of StarCoder: fine-tuning & inference!

The Mojo Programming Language

🔊 Text-Prompted Generative Audio Model

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Trace variables and the operations on them using graphviz visualizations.