#transformer on Hacker News

6 stories tagged transformer, newest first.

Screenshot of github.com: I built a neural network using DOOM games

I built a neural network using DOOM games (github.com)

4 points by falperc 4 days ago | 1 comments

GitHub repo for Doomformer, which computes neural networks including transformers using DOOM game mechanics like voodoo dolls, conveyor belts, lava and doors, verified bit-exact.

doom neural-networks esoteric-computing transformer

Screenshot of github.com: Show HN: TurboGPT: train 22KiB transformer in 13s

Show HN: TurboGPT: train 22KiB transformer in 13s (github.com)

41 points by lostmsu 26 days ago | 5 comments

GitHub repository for TurboGPT, a CUDA-only project for training a tiny GPT transformer in under a minute, inspired by minGPT.

transformer gpt cuda pytorch

Screenshot of github.com: Show HN: I built a tiny LLM to demystify how language models work

Show HN: I built a tiny LLM to demystify how language models work (github.com)

827 points by armanified 6 months ago | 125 comments

GitHub repository for GuppyLM, a ~9M parameter transformer language model built from scratch in PyTorch that talks like a small fish.

llm transformer pytorch small-language-models

Screenshot of jalammar.github.io: The Illustrated Transformer

The Illustrated Transformer (jalammar.github.io)

468 points by auraham 10 months ago | 85 comments

Jay Alammar's illustrated blog post explaining the Transformer neural network architecture and its self-attention mechanism with visual diagrams.

transformer attention deep-learning nlp

Screenshot of github.com: RustGPT: A pure-Rust transformer LLM built from scratch

RustGPT: A pure-Rust transformer LLM built from scratch (github.com)

357 points by amazonhut 1 year ago | 170 comments

GitHub repository for RustGPT, a transformer-based large language model written entirely in Rust from scratch.

rust transformer llm from-scratch

Screenshot of docs.likejazz.com: Llama 3 implemented in pure NumPy

Llama 3 implemented in pure NumPy (docs.likejazz.com)

404 points by orixilus 2 years ago | 48 comments

GitHub repository llama3.np, a pure NumPy implementation of the Llama 3 language model for inference.

llama-3 numpy python llm

#transformer on Hacker News

I built a neural network using DOOM games(github.com)

Show HN: TurboGPT: train 22KiB transformer in 13s(github.com)

Show HN: I built a tiny LLM to demystify how language models work(github.com)

The Illustrated Transformer(jalammar.github.io)

RustGPT: A pure-Rust transformer LLM built from scratch(github.com)

Llama 3 implemented in pure NumPy(docs.likejazz.com)