Register hailo library with .hef download counting

[evandhoffman]

Adds a hailo library entry to model-libraries.ts so that HEF (Hailo Executable Format) files hosted on the Hub get counted toward download stats.

Why

Hailo makes the Hailo-8 / Hailo-15 PCIe AI accelerators (commonly seen as M.2 add-ons for the Raspberry Pi 5 AI Kit and other edge platforms). Models targeting these chips are compiled to .hef binaries via Hailo's Dataflow Compiler; the HEF is the actual deployment artifact, similar in role to a TensorRT engine or a CoreML .mlpackage.

Hailo's own model zoo is hosted on GitHub today, but third-party projects are starting to publish HEFs on the Hub alongside their source weights — e.g. k10z/birdvision-efficientnet-s (a fine-tuned EfficientNet-V2-S for bird species classification compiled to Hailo-8). These repos currently show no download counts because the Hub's default query files (config.json, config.yaml, etc.) aren't matched.

What this does

Registers hailo with countDownloads: path_extension:"hef", matching the pattern used for other accelerator-binary libraries (e.g. HoloMotion using path_extension:"onnx").

hailo: {
    prettyLabel: "Hailo",
    repoName: "hailort",
    repoUrl: "https://github.com/hailo-ai/hailort",
    countDownloads: `path_extension:"hef"`,
    snippets: snippets.hailo,
    filter: false,
},

repoUrl points at the public hailort runtime — the end-user dependency that actually loads HEFs at inference time.

Snippet is a minimal Hub-aware load pattern (hf_hub_download + HEF + VDevice) with a pointer to the hailort repo for the full inference API.

Pre-merge checklist

• Inserted alphabetically between habibi-tts and hallo
• filter: false per the integration guide
• At least one model on the Hub declares library_name: hailo: k10z/birdvision-efficientnet-s
• Bugbot review clean

[evandhoffman]

Updated to match the integration guide more precisely after reviewing it:

• Added filter: false (per "set filter to false")
• Added a Python loader snippet in model-libraries-snippets.ts referencing the typical hailo_platform API (VDevice, HEF, create_infer_model)
• Confirmed at least one model already declares library_name: hailo: k10z/birdvision-efficientnet-s

[Wauplin]

Hi @evandhoffman thanks for the PR and details. From what I can see in https://huggingface.co/models?other=hailo:

• https://huggingface.co/n2b8/backyard-birds doesn't have .hef files
• https://huggingface.co/EdgeFirst/yolov5-det/tree/main and all other yolo edgefirst models have .hef files among other formats => it means download count will brake for e.g. .onnx files
• same for https://huggingface.co/cstr/all-MiniLM-L6-v2-hailo10h/tree/main and others (onnx alongside hef)

I feel that if hef is a file format we don't have a good way of counting them. If hailo is indeed a library, it's best to split these files to separate repos so we don't double-count or under-count download (i.e. have a .onnx repo and a .hef repo, both with there own counter). Alternative is to add both .hef and .onnx to download counter rule for hailo but that would be relevant only if hailo really support .onnx (which is not the case I think)

[julien-c]

cc @danbev for viz btw