DeiT3_Base_Patch16_224

aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/DeiT3_Base_Patch16_224). 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 0.83782, top5_accuracy 0.96572. Only the evaluated core mode was measured.

SHA-256: 53f1337dcca48a44ece148b095fb8c8bb0015eb5e94d23d96b6155816ac20b79 (101838849 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": "DeiT3_Base_Patch16_224",
  "variant": "c0923-asym-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": 0.83782
    },
    "secondary": {
      "top5_accuracy": 0.96572
    },
    "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": 99.99522593273339
  },
  "content_sha256": "fc5505e252c7c6286369026ba7a7797c4c33486c3d117c5dfc9ee7e4f353969a",
  "attempt_id": "DeiT3_Base_Patch16_224-jinman-20261017t104552-63e24",
  "superseded_attempt_ids": [],
  "sha256": "53f1337dcca48a44ece148b095fb8c8bb0015eb5e94d23d96b6155816ac20b79",
  "format": "MXQv7",
  "supported_modes": [
    "single"
  ],
  "size": 101838849,
  "ops_commits": {
    "selection": "9c9a469c2a5f34dd9650f972b289e1bfdf438c27"
  },
  "arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/DeiT3_Base_Patch16_224",
  "publication": {
    "status": "public",
    "reason": "approved"
  }
}
Downloads last month
64
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mobilint/DeiT3_Base_Patch16_224

Quantized
(1)
this model

Collection including mobilint/DeiT3_Base_Patch16_224