Downloads · 30 days
82
38% of all-time downloads
mobilint/DeiT3_Base_Patch16_384
DeiT3_Base_Patch16_384 is a image classification model from mobilint. Use it when you need a label for an image. It is set up for mobilint. The card lists the license as apache-2.0.
aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/imageclassification/DeiT3BasePatch16384). It was compiled by qbcompiler 1.3.0 in the im…
Downloads · 30 days
82
38% of all-time downloads
All-time downloads
215
Public
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.onnx348 MB · 77%
From the Hugging Face model README
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_384). It was compiled by qbcompiler 1.3.0 in the image mobilint/qbcompiler:1.3-cuda12.8.1-ubuntu22.04 (sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7) 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 0.8505, top5_accuracy 0.97224. Only the evaluated core mode was measured.
SHA-256: 056ca39247e02f81eed1295fd18ccfac622194fd83b45ff00c514e8b1e9da2c6 (103554405 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_384",
"variant": "asym",
"qbcompiler": "1.3.0",
"qbruntime": "1.5.0",
"compile": {
"image_tag": "1.3-cuda12.8.1-ubuntu22.04",
"image_digest": "sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7",
"inference_scheme": "single",
"device": "gpu"
},
"evaluation": {
"dataset": "imagenet",
"sample_count": 50000,
"primary": {
"top1_accuracy": 0.8505
},
"secondary": {
"top5_accuracy": 0.97224
},
"protocol": null,
"eval_data_identity": null,
"identity_audit": "absent",
"inference_mode": "async",
"image_tag": "1.3-cpu-ubuntu22.04",
"image_digest": "sha256:7c25b894fc0807acdf27f15c61b910b96dc66d3f5d97e04b595b2d7a8008e77c"
},
"retention_percent": {
"top1_accuracy": 99.96238922451283
},
"content_sha256": "0facc2ca33e6eec7a4d9eb227e7c4d0e10f1a12555dcadc1e656a91005c69e7c",
"attempt_id": "DeiT3_Base_Patch16_384-jinman-20261017t142730-c76c8",
"superseded_attempt_ids": [],
"sha256": "056ca39247e02f81eed1295fd18ccfac622194fd83b45ff00c514e8b1e9da2c6",
"format": "MXQv7",
"supported_modes": [
"single"
],
"size": 103554405,
"ops_commits": {
"selection": "9c9a469c2a5f34dd9650f972b289e1bfdf438c27"
},
"arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/DeiT3_Base_Patch16_384",
"publication": {
"status": "public",
"reason": "approved"
}
}