Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

AICI: Prompts as (Wasm) Programs

Rust-tokenizer offers high-performance tokenizers for modern language models, including WordPiece, Byte-Pair Encoding (BPE) and Unigram (SentencePiece) models

Rust powered waveform source separation

Implementation of the GPT architecture in Rust 🦀 + Burn 🔥

A GPT Implementation in Rust on top of tch-rs 🔥 🦀

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

Port of Andrej Karpathy's python microGPT to Rust

AthenaOS is a next generation AI-native operating system managed by Swarms of AI Agents

Train small sequence models in your browser with WebGPU.

Succeeded by SyntaxDot: https://github.com/tensordot/syntaxdot

🦀 TrustOS — Bare-metal OS with a 4.4M-param AI transformer in the kernel. 257K lines of pure Rust, zero C. Desktop, browser, emulators, native compiler, mesh networking. x86_64/ARM64/RISC-V. Built solo by @Nated0ge.

Succeeded by syntaxdot-transformers: https://github.com/tensordot/syntaxdot/tree/main/syntaxdot-transformers

Further developed as SyntaxDot: https://github.com/tensordot/syntaxdot

burn inference and training of baby dragon hatchling 🔥🐉

Parsing and JSON transformer library for the OpenFGA authorization DSL

A language-agnostic deep learning framework for decoupled model definition and execution.

Rust Implemention of paper: Attention Is All You Need(https://arxiv.org/abs/1706.03762), Code Port from http://nlp.seas.harvard.edu/2018/04/03/attention.html

🦀 一个高性能的 JavaScript/TypeScript 代码转换器，基于 Rust 和 SWC

A project written in the Rust language with the goal of offline load of small LLM Model, specifically RAG (Retrieval Augmented Generation) on mobile devices.