Brainfuck interpreter inside printf

Dataset and benchmarks for Language identification and content detection for low-resource languages

About A collection of AWESOME things about information geometry Topics

LLM training in simple, raw C/CUDA

Deep learning library

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Machine Learning Engineering Open Book

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Spotify/Annoy-inspired Approximate Nearest Neighbors in Rust, based on LMDB and optimized for memory usage 💥

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Sparsity-aware deep learning inference runtime for CPUs

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

A simple & elegant experiment tracking framework that integrates persistence logic & best practices directly into Python

🦉 ML Experiments and Data Management with Git

Production-Grade Container Scheduling and Management

All Algorithms implemented in Python

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

[CVPR 2024] ViT-Lens: Towards Omni-modal Representations

Open source codebase powering the HuggingChat app

Software Architecture for ML engineers

Turn expensive prompts into cheap fine-tuned models

Tensor library for machine learning

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

PyTorch extensions for high performance and large scale training.

The first real AI developer

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.