Model reference · open weights
aim-large-patch14-224 is an open-weight embedding model from apple. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | apple |
|---|---|
| Type | Embedding models |
| Task | Image embed |
| Parameters (lead) | 309M |
| Runs with | transformers |
| Released | 2024-10-29 |
| Popularity | 1k downloads / month |
| Licence | Commercial licence needed |
About
[AIMv2 Paper] [BibTeX]
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:
import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModel
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
processor = AutoImageProcessor.from_pretrained(
"apple/aimv2-large-patch14-224",
revision="ac764a25c832c7dc5e11871daa588e98e3cdbfb7",
)
model = AutoModel.from_pretrained(
"apple/aimv2-large-patch14-224",
revision="ac764a25c832c7dc5e11871daa588e98e3cdbfb7",
trust_remote_code=True,
)
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
import requests
from PIL import Image
from transformers import AutoImageProcessor, FlaxAutoModel
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
processor = AutoImageProcessor.from_pretrained(
"apple/aimv2-large-patch14-224",
)
model = FlaxAutoModel.from_pretrained(
"apple/aimv2-large-patch14-224",
trust_remote_code=True,
)
inputs = processor(images=image, return_tensors="jax")
outputs = model(**inputs)
If you find our work useful, please consider citing us as:
@misc{fini2024multimodalautoregressivepretraininglarge,
author = {Fini, Enrico and Shukor, Mustafa and Li, Xiujun and Dufter, Philipp and Klein, Michal and Haldimann, David and Aitharaju, Sai and da Costa, Victor Guilherme Turrisi and Béthune, Louis and Gan, Zhe and Toshev, Alexander T and Eichner, Marcin and Nabi, Moin and Yang, Yinfei and Susskind, Joshua M. and El-Nouby, Alaaeldin},
url = {https://arxiv.org/abs/2411.14402},
eprint = {2411.14402},
eprintclass = {cs.CV},
eprinttype = {arXiv},
title = {Multimodal Autoregressive Pre-training of Large Vision Encoders},
year = {2024},
}
From the published model card. Full card on the HuggingFace links in the sidebar.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Classification | imagenet-1k | Accuracy | 86.600 |
| Classification | inaturalist-18 | Accuracy | 76 |
| Classification | cifar10 | Accuracy | 99.100 |
| Classification | cifar100 | Accuracy | 92.200 |
| Classification | food101 | Accuracy | 95.700 |
| Classification | dtd | Accuracy | 87.900 |
| Classification | oxford-pets | Accuracy | 96.300 |
| Classification | stanford-cars | Accuracy | 96.300 |
| Classification | camelyon17 | Accuracy | 93.700 |
| Classification | patch-camelyon | Accuracy | 89.300 |
| Classification | rxrx1 | Accuracy | 5.600 |
| Classification | eurosat | Accuracy | 98.400 |
| Classification | fmow | Accuracy | 60.700 |
| Classification | domainnet-infographic | Accuracy | 69 |
Using it via the API
Once AxForge deploys aim-large-patch14-224 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (aim-large-patch14-224 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"aim-large-patch14-224","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.