LeViT_128

aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/LeViT_128). It was compiled by qbcompiler 1.4.0 in the image mobilint/qbcompiler:1.4-cuda12.8.1-ubuntu22.04 (sha256:7910f1661605b82eb9616f6ac99fd6461dbb865dcadaa810cce22c638ceffd44) with --inference-scheme single, so it supports the core mode(s) single only.

It was evaluated with qbruntime 1.5.0 in async inference mode on imagenet (50000 samples): top1_accuracy 0.78144, top5_accuracy 0.9374. Only the evaluated core mode was measured.

SHA-256: 61f3af24f306e8032e62769c05d67d9ce9a3d039d7383f9251fb6dc90b9eed8c (14623272 bytes). Verify a download with sha256sum <file>.mxq and compare the digest with this value and with aries-rb/metadata.json.

aries-rb/best_result.json contains legacy build values and is retained for mblt-vision-python compile defaults. The legacy aries/ directory was removed; mblt-model-zoo <= 2.12 must pin an older revision.

{
  "schema_version": 2,
  "model": "LeViT_128",
  "variant": "c0923-gptaq",
  "qbcompiler": "1.4.0",
  "qbruntime": "1.5.0",
  "compile": {
    "image_tag": "1.4-cuda12.8.1-ubuntu22.04",
    "image_digest": "sha256:7910f1661605b82eb9616f6ac99fd6461dbb865dcadaa810cce22c638ceffd44",
    "inference_scheme": "single",
    "device": "gpu"
  },
  "evaluation": {
    "dataset": "imagenet",
    "sample_count": 50000,
    "primary": {
      "top1_accuracy": 0.78144
    },
    "secondary": {
      "top5_accuracy": 0.9374
    },
    "protocol": null,
    "eval_data_identity": null,
    "identity_audit": "absent",
    "inference_mode": "async",
    "image_tag": "1.4-cpu-ubuntu22.04",
    "image_digest": "sha256:62b5bc714571dffd94fb561275767ca80d15337a433630a3ae7936305d531a7b"
  },
  "retention_percent": {
    "top1_accuracy": 99.57947855340623
  },
  "content_sha256": "151b4a9366969a1fdc9f5ae22eca4489aaa796407d0f0a4e2659e69efce5b2eb",
  "attempt_id": "LeViT_128-jinman-20261017t130015-9e6f2",
  "superseded_attempt_ids": [],
  "sha256": "61f3af24f306e8032e62769c05d67d9ce9a3d039d7383f9251fb6dc90b9eed8c",
  "format": "MXQv7",
  "supported_modes": [
    "single"
  ],
  "size": 14623272,
  "ops_commits": {
    "selection": "9c9a469c2a5f34dd9650f972b289e1bfdf438c27"
  },
  "arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/LeViT_128",
  "publication": {
    "status": "public",
    "reason": "approved"
  }
}