Downloads · 30 days
67
10% of all-time downloads
justinchuby/onnx-genai-example-qwen2-5-0-5b-cuda-gqa-f16
onnx-genai-example-qwen2-5-0-5b-cuda-gqa-f16 is a machine learning model from justinchuby. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Private real-weight ONNX package produced by Mobius from Qwen/Qwen2.5-0.5B-Instruct at immutable revision 7ae557604adf67be50417f59c2c2f167def9a775. Source license: apache-2.0.
Downloads · 30 days
67
10% of all-time downloads
All-time downloads
666
Public
Repo size
994 MB
Likes
0
Public
Click a slice to open those files.
.data994 MB · 99%
From the Hugging Face model README
Private real-weight ONNX package produced by Mobius from
Qwen/Qwen2.5-0.5B-Instruct at immutable revision
7ae557604adf67be50417f59c2c2f167def9a775. Source license: apache-2.0.
This package contains 24 CUDA com.microsoft::GroupQueryAttention nodes.
weight_integrity.json validates every packed QKV initializer against the
pinned source weights.
inference_metadata.yamlrequest.json and output.json real runtime evidencegraph_report.json, performance.json, source.json, and provenance.jsonObserved output: Write one short sentence about ONNX. ONNX is a popular open-source framework
hf download justinchuby/onnx-genai-example-qwen2-5-0-5b-cuda-gqa-f16 --repo-type model --local-dir ./qwen2.5-0.5b-cuda-gqa-f16
python - <<'PY'
from pathlib import Path
import onnxruntime as ort
root = Path("qwen2.5-0.5b-cuda-gqa-f16")
for relative_path in ['model.onnx']:
session = ort.InferenceSession(
str(root / relative_path),
providers=['CUDAExecutionProvider', '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.
Review inference_metadata.annotated.yaml for inline explanations of this package's workflow, tensor/state/cache contracts, and fail-closed omissions. inference_metadata.yaml remains the canonical machine-authored contract; automated validation confirms both files parse to the same metadata object.