---
title: BiomedCLIP-PubMedBERT_256-vit_base_patch16_224
description: BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning. It uses PubMedBERT as the text encoder and Vision Transformer as the image encoder, with domain-specific adaptations. It can perform various vision-language processing…
tags:
- biology
- clip
- en
- literature
- medical
- nlp
- open_clip
license: mit
source_url: https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224
---

# BiomedCLIP-PubMedBERT_256-vit_base_patch16_224

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning. It uses PubMedBERT as the text encoder and Vision Transformer as the image encoder, with domain-specific adaptations. It can perform various vision-language processing…

Upstream identifier: `microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224`.

**Source:** https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224

**Licence:** mit

_This model is part of the Atlas demo catalogue. See the repository history for provenance._