---
license: mit
tags:
- onnx
- onnxruntime
- onnx-genai
- inference-metadata
---

# onnx-genai-example-esm2-t6-8m

Private real-weight ONNX package produced by Mobius from
[`facebook/esm2_t6_8M_UR50D`](https://huggingface.co/facebook/esm2_t6_8M_UR50D/tree/c731040fcd8d73dceaa04b0a8e6329b345b0f5df) at immutable revision
`c731040fcd8d73dceaa04b0a8e6329b345b0f5df`. Source license: `mit`.

## Contents

- Canonical, hashless `inference_metadata.yaml`
- ONNX graphs and external-data weights
- Complete tokenizer/processor assets
- `request.json` and `output.json` real runtime evidence
- `graph_report.json`, `performance.json`, `source.json`, and `provenance.json`

Observed output: `embedding norm 7.5770978927612305`

## Exact download

```bash
hf download justinchuby/onnx-genai-example-esm2-t6-8m --repo-type model --local-dir ./esm2-t6-8m
```

## ONNX Runtime load smoke test

```bash
python - <<'PY'
from pathlib import Path
import onnxruntime as ort

root = Path("esm2-t6-8m")
for relative_path in ['model.onnx']:
    session = ort.InferenceSession(
        str(root / relative_path),
        providers=['CPUExecutionProvider'],
    )
    print(relative_path, session.get_providers(), [x.name for x in session.get_inputs()])
PY
```

The exact successful probe request, output, versions, providers, and timings are
preserved in `request.json`, `output.json`, and `performance.json`.

<!-- inference-metadata-annotation:start -->
## Annotated inference metadata

Review [`inference_metadata.annotated.yaml`](./inference_metadata.annotated.yaml) for inline explanations of this package's workflow, tensor/state/cache contracts, and fail-closed omissions. [`inference_metadata.yaml`](./inference_metadata.yaml) remains the canonical machine-authored contract; automated validation confirms both files parse to the same metadata object.
<!-- inference-metadata-annotation:end -->