Skip to content
ModelListedExternal
Download

Hiera Huge 224 Hf

with ONNX weights to be compatible with Transformers.js.

KindOtherBase modelfacebook/hiera-huge-224-hfVersionRevision 14e2067

Model source

Kind
Other
File size
1.41 MB–1.25 GB
Base model
facebook/hiera-huge-224-hf
Version
vRevision 14e2067
Updated
Sep 16, 2026
Downloads
8
Source
Hugging Face

Source description

https://huggingface.co/facebook/hiera-huge-224-hf with ONNX weights to be compatible with Transformers.js.

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Sources

1 source
Hugging FacePrimaryVersion 14e2067e0248917d09cc47c1faea328183427be1
huggingface.co/onnx-community/hiera-huge-224-hf/tree/14e2067e0248917d09cc47c1faea328183427be1

Verified Sep 16

Model artifacts

8 artifacts

onnx/model_bnb4.onnx

onnx · 366 MB · SHA-256 f1cb94c3d274…1126 · Hugging Face

Download

onnx/model_fp16.onnx

onnx · 1.25 GB · SHA-256 a7ce892eaba4…6c8b · Hugging Face

Download

onnx/model_int8.onnx

onnx · 647 MB · SHA-256 ac537c52e73e…b2d4 · Hugging Face

Download

onnx/model_q4.onnx

onnx · 406 MB · SHA-256 25ecc24a57b8…30a9 · Hugging Face

Download

onnx/model_q4f16.onnx

onnx · 363 MB · SHA-256 2cba2380d6dc…bd3a · Hugging Face

Download

onnx/model_quantized.onnx

onnx · 647 MB · SHA-256 2e030373e824…3c9a · Hugging Face

Download

onnx/model_uint8.onnx

onnx · 647 MB · SHA-256 2e030373e824…3c9a · Hugging Face

Download

onnx/model.onnx

onnx · 1.41 MB · SHA-256 55b47e5897ef…66b2 · Hugging Face

Download

Source excerpts

2 excerpts

--- base_model: facebook/hiera-huge-224-hf library_name: transformers.js --- https://huggingface.co/facebook/hiera-huge-224-hf with ONNX weights to be compatible with Transformers.js. Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

Source context: 8 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers.js · Repo onnx-community/hiera-huge-224-hf