Stories by tosh

The Dragon in My Garage

Model Stock: All we need is just a few fine-tuned models

Breaking Silos

Transforming the Web: The End of Silos

Instructor: Structured Data Like JSON from Large Language Models

Model Stock: All we need is just a few fine-tuned models

Mini-Jamba

Editing Models with Task Arithmetic (2022)

Slerp

Orcid and GitHub Sign Memorandum of Understanding

Instruction-Following Evaluation for Large Language Models

LazyMergekit

Tips for LLM Pretraining and Evaluating Reward Models

Starling LM 7B Beta

WebGPT: GPT Model on the Browser with WebGPU

Links

Nectar

First Council of Nicaea

Mistral-7B Playing Doom

What is a coder's worst nightmare? (2016)