Aimv2 3B Patch14 448
We introduce the AIMv2 family of vision models pre-trained with a multimodal autoregressive objective. AIMv2 pre-training is simple and straightforward to train and scale effectively. Some AIMv2 highlights include:
Model source
- Kind
- Other
- File size
- 960 MB–10.1 GB
- Version
- vRevision 3501a91
- Updated
- Sep 22, 2026
- Downloads
- 394
- Source
- Hugging Face
Source excerpt
We introduce the AIMv2 family of vision models pre-trained with a multimodal autoregressive objective. AIMv2 pre-training is simple and straightforward to train and scale effectively. Some AIMv2 highlights include:
Sources
1 source
Sources
1 sourceVerified Sep 9
Model artifacts
5 artifacts
Model artifacts
5 artifactsmodel-00001-of-00003.safetensors
safetensors · 4.57 GB · SHA-256 dd819ea84275…058e · Hugging Face
Downloadmodel-00002-of-00003.safetensors
safetensors · 4.64 GB · SHA-256 5fbcf46425d1…1bde · Hugging Face
Downloadmodel-00003-of-00003.safetensors
safetensors · 960 MB · SHA-256 d480a95d8c05…daab · Hugging Face
DownloadSource excerpts
2 excerpts
Source excerpts
2 excerpts--- library_name: transformers license: apple-amlr metrics: - accuracy pipeline_tag: image-feature-extraction tags: - vision - image-feature-extraction - mlx - pytorch model-index: - name: aimv2-3B-patch14-448 results: - task: type: classification name: Classification dataset: name: imagenet-1k type: imagenet-1k metrics: - type: accuracy value: 89.5 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: inaturalist-18 type: inaturalist-18 metrics: - type: accuracy value: 85.9 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: cifar10 type: cifar10 metrics: - type: accuracy value: 99.5 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: cifar100 type: cifar100 metrics: - type: accuracy value: 94.5 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: food101 type: food101 metrics: - type: accuracy value: 97.4 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: dtd type: dtd metrics: - type: accuracy value: 89.0 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: oxford-pets type: oxford-pets metrics: - type: accuracy value: 97.4 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: stanford-cars type: stanford-cars metrics: - type: accuracy value: 96.7 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: camelyon17 type: camelyon17 metrics: - type: accuracy value: 93.4 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: patch-camelyon type: patch-camelyon metrics: - type: accuracy value: 89.9 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: rxrx1 type: rxrx1 metrics: - type: accuracy value: 9.5 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: eurosat type: eurosat metrics: - type: accuracy value: 98.9 name: Accuracy verified: false - task: type: classification name: Classification dataset: name: fmow type: fmow metrics: - type: accuracy value:...
Source context: 394 downloads · 15 likes · Pipeline image-feature-extraction · Library transformers · Repo apple/aimv2-3B-patch14-448
