model roundup

GPT 2

3 items · started 2026-09-01 · closed 2026-09-05

  1. Running LLMs in the Browser with Three.js A tour of how language models generate text, how GPT-2 and newer Phi and Qwen architectures differ, and how Three-LLM implements their inference graphs with Three.js TSL compute shaders. Ben Housto…

  2. LLMs receive sequences of token IDs instead of raw text. For example, the GPT-2 tokenizer encodes what's the weather in goldshire?

  3. Heaviside-1 was trained on 500B field samples from over 250K unique physical layout designs, and is approximately the scale of GPT-2. It predicts a full design's fields ~10^5x faster than a commercial full-wave solver, with S-parameter mag…

← all threads