Model Normalize

Normalize an HF model checkpoint — quantize bf16/fp16 weights to per-block FP8, and/or repack engine-named safetensors into HF-standard ~4GB shards.

InternLM Updated
Picture from the README

File contents

internlm/xtuner commit 9f72e3bfe9

Frequently asked questions

npx get-skill add internlm/model-normalize