Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Dpt Dinov2 Base Nyu

with ONNX weights to be compatible with Transformers.js.

ArtOtherBasismodellfacebook/dpt-dinov2-base-nyuVersionRevision 853987dCBewertung

Modellquelle

Art
Other
Dateigröße
88,8–423 MB
Basismodell
facebook/dpt-dinov2-base-nyu
Version
vRevision 853987d
Aktualisiert
20. Okt. 2026
Downloads
6
Quelle
Hugging Face

Quellenbeschreibung

https://huggingface.co/facebook/dpt-dinov2-base-nyu 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).

Quellen

1 Quelle
Hugging FacePrimärVersion 853987df5ef269f514cb626d124d6387220e914d
huggingface.co/onnx-community/dpt-dinov2-base-nyu/tree/853987df5ef269f514cb626d124d6387220e914d

Verifiziert 17. Aug.

Modellartefakte

8 Artefakte

onnx/model_bnb4.onnx

onnx · 129 MB · SHA-256 090c3f448a29…fc21 · Hugging Face

Herunterladen

onnx/model_fp16.onnx

onnx · 212 MB · SHA-256 d2d31fcc509f…a854 · Hugging Face

Herunterladen

onnx/model_int8.onnx

onnx · 111 MB · SHA-256 517c773daa75…c320 · Hugging Face

Herunterladen

onnx/model_q4.onnx

onnx · 134 MB · SHA-256 2d657de845e8…c5ba · Hugging Face

Herunterladen

onnx/model_q4f16.onnx

onnx · 88,8 MB · SHA-256 161bf182a03b…c3ed · Hugging Face

Herunterladen

onnx/model_quantized.onnx

onnx · 111 MB · SHA-256 232a073a9bc0…9267 · Hugging Face

Herunterladen

onnx/model_uint8.onnx

onnx · 111 MB · SHA-256 232a073a9bc0…9267 · Hugging Face

Herunterladen

onnx/model.onnx

onnx · 423 MB · SHA-256 23bbe4564089…3cbf · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

--- base_model: facebook/dpt-dinov2-base-nyu library_name: transformers.js --- https://huggingface.co/facebook/dpt-dinov2-base-nyu 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: 6 downloads · 0 likes · Pipeline depth-estimation · Library transformers.js · Repo onnx-community/dpt-dinov2-base-nyu