ModelListedExternal

Medsam Vit Base

with ONNX weights to be compatible with Transformers.js.

Sourcehuggingface.co/Xenova/medsam-vit-base/tree/6603f595096e4ce74e2efbdb2af774bf11e2774d

KindOtherBase modelwanglab/medsam-vit-baseVersionRevision 6603f59Bgrade

Model source

Kind: Other
File size: 4.68–343 MB
Base model: wanglab/medsam-vit-base
Version: vRevision 6603f59
Updated: Oct 10, 2026
Downloads: 64
Source: Hugging Face

Source description

https://huggingface.co/wanglab/medsam-vit-base 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 6603f595096e4ce74e2efbdb2af774bf11e2774d

huggingface.co/Xenova/medsam-vit-base/tree/6603f595096e4ce74e2efbdb2af774bf11e2774d

Verified Oct 10

Download files

Model artifacts

6 artifacts

onnx/prompt_encoder_mask_decoder_fp16.onnx

onnx · 8.15 MB · SHA-256 ae37ca711560…4d97 · Hugging Face

Download file

onnx/prompt_encoder_mask_decoder_quantized.onnx

onnx · 4.68 MB · SHA-256 49784edc1cb3…46d4 · Hugging Face

Download file

onnx/prompt_encoder_mask_decoder.onnx

onnx · 15.8 MB · SHA-256 6d33b56fb067…55ab · Hugging Face

Download file

onnx/vision_encoder_fp16.onnx

onnx · 172 MB · SHA-256 806b471147ba…cc8b · Hugging Face

Download file

onnx/vision_encoder_quantized.onnx

onnx · 96.4 MB · SHA-256 d9d7bca3b256…d247 · Hugging Face

Download file

onnx/vision_encoder.onnx

onnx · 343 MB · SHA-256 238f9a4496b1…2ae5 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeAug 1huggingface.co/Xenova/medsam-vit-base

--- base_model: wanglab/medsam-vit-base library_name: transformers.js license: apache-2.0 --- https://huggingface.co/wanglab/medsam-vit-base 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`).

NoteOct 10huggingface.co/Xenova/medsam-vit-base

Source context: 64 downloads · 0 likes · Pipeline mask-generation · Library transformers.js · Repo Xenova/medsam-vit-base

NoteAug 1huggingface.co/Xenova/medsam-vit-base

Source context: 40 downloads · 0 likes · Pipeline mask-generation · Library transformers.js · Repo Xenova/medsam-vit-base