PUBLISH.md

# Publish this folder as a Hugging Face model repo

This directory is a **standalone** git repository. It is ignored by the parent
`glucofm` code repo (see root `.gitignore`: `/artifacts/`).

## Regenerate weights

From the parent crate:

```bash
cargo run --release --features infer,onnx --example convert_weights -- \
  --from artifacts/glucofm_encoder.onnx --all artifacts/
cd artifacts && shasum -a 256 glucofm_encoder.* config.json LICENSE README.md PUBLISH.md \
  | sort -k2 > SHA256SUMS
```

## One-time setup

```bash
cd artifacts
# already initialized if you used the prep script; otherwise:
#   git init
#   git lfs install
#   git lfs track "*.onnx" "*.safetensors" "*.gguf" "*.rlxp" "*.bin"

huggingface-cli login
# Create an empty model repo on HF (web UI or):
#   huggingface-cli repo create glucofm-encoder --type model

git remote add origin https://huggingface.co/<USER>/glucofm-encoder
git add -A
git commit -m "Add GlucoFM encoder weights (safetensors, GGUF, RLXP, ONNX, bin)"
git push -u origin main
```

## Verify checksums

```bash
shasum -a 256 -c SHA256SUMS
```

## Suggested Hub id

`glucofm-encoder` (or `<org>/glucofm-encoder`). After publish, point the
parent crate README / `OPENCGM_HF_*` docs at that id if you replace the
upstream OpenCGM download path.