Get the latest tech news

RustGPT: A pure-Rust transformer LLM built from scratch


An transformer based LLM. Written completely in Rust - tekaratzas/RustGPT

Pre-training on factual text completion Instruction tuning for conversational AI Interactive chat mode for testing Full backpropagation with gradient clipping Modular architecture with clean separation of concerns Custom tokenization with punctuation handling Greedy decoding for text generation Gradient clipping for training stability Modular layer system with clean interfaces Comprehensive test coverage for all components Follow standard Rust conventions ( cargo fmt) Add comprehensive tests for new features Update documentation and README as needed Keep the "from scratch" philosophy - avoid heavy ML dependencies

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Scratch

Scratch

Photo of LLM

LLM

Photo of RustGPT

RustGPT

Related news:

News photo

Writing an operating system kernel from scratch

News photo

SkiftOS: A hobby OS built from scratch using C/C++ for ARM, x86, and RISC-V

News photo

VaultGemma: The most capable differentially private LLM