Instructions to use mobilint/RepViT_M2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Mobilint
How to use mobilint/RepViT_M2 with Mobilint:
# pip install mblt-model-zoo from mblt_model_zoo.vision import MBLT_Engine model = MBLT_Engine( model_cls="RepViT_M2", model_type="DEFAULT", model_path="", core_mode="global8", ) try: image = model.preprocess("path/to/image.jpg") output = model(image) result = model.postprocess(output) finally: model.dispose() - Notebooks
- Google Colab
- Kaggle
RepViT_M2
aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/RepViT_M2). 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 all, so it supports the core mode(s) single, multi, global4, global8 only.
It was evaluated with qbruntime 1.5.0 in async inference mode on imagenet (50000 samples): top1_accuracy 0.79952, top5_accuracy 0.9484. Only the evaluated core mode was measured.
SHA-256: 8d94c09c3e221341da72202f399d408ff951c091e9d6f9abca8f9d727c132c89 (9561784 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": "RepViT_M2",
"variant": "bias-corr-postact",
"qbcompiler": "1.3.0",
"qbruntime": "1.5.0",
"compile": {
"image_tag": "1.3-cuda12.8.1-ubuntu22.04",
"image_digest": "sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7",
"inference_scheme": "all",
"device": "gpu"
},
"evaluation": {
"dataset": "imagenet",
"sample_count": 50000,
"primary": {
"top1_accuracy": 0.79952
},
"secondary": {
"top5_accuracy": 0.9484
},
"protocol": null,
"eval_data_identity": {
"annotation_sha256": "f00550c10ff1d4110abc683786b6cc09d5082dadd3cee1568f5cfa1dad962960",
"sample_list_sha256": "54446819dced83110352e5a0361ff05b19c331c5a9802dcb0222e6d1e44a0547"
},
"identity_audit": "verified",
"inference_mode": "async",
"image_tag": "1.3-cpu-ubuntu22.04",
"image_digest": "sha256:7c25b894fc0807acdf27f15c61b910b96dc66d3f5d97e04b595b2d7a8008e77c"
},
"retention_percent": {
"top1_accuracy": 99.35875130486653
},
"content_sha256": "a66e3bfc66de9261ddea3a631ae0571c6d175de6b864ba864328925675ca9d47",
"attempt_id": "RepViT_M2-jinman-coreall-2195f1393af3",
"superseded_attempt_ids": [],
"sha256": "8d94c09c3e221341da72202f399d408ff951c091e9d6f9abca8f9d727c132c89",
"format": "MXQv7",
"supported_modes": [
"single",
"multi",
"global4",
"global8"
],
"size": 9561784,
"ops_commits": {
"selection": "6cc61b6c4600f8afef654f68ee851d2b65ebac1e"
},
"arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/RepViT_M2",
"publication": {
"status": "public",
"reason": "approved"
}
}
- Downloads last month
- 31
Model tree for mobilint/RepViT_M2
Base model
timm/repvit_m2.dist_in1k