# Visual Salamandra: Pushing the Boundaries of Multimodal Understanding

DevFeed: [Visual Salamandra: Pushing the Boundaries of Multimodal Understanding](<https://devfeed.tech/articles/visual-salamandra-pushing-the-boundaries-of-multimodal-understanding-6990.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/BSC-LT/visualsalamandra7b>)

Author: Iñigo Pikabea; Jaume Lozano

Published: 2025-04-11T14:21:56Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [mlp](<https://devfeed.tech/topics/mlp.md>), [AI Research](<https://devfeed.tech/topics/ai-research.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [blog](<https://devfeed.tech/tags/blog.md>), [blog-post](<https://devfeed.tech/tags/blog-post.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [language](<https://devfeed.tech/tags/language.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mlp](<https://devfeed.tech/tags/mlp.md>), [models](<https://devfeed.tech/tags/models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [multimodal-ai](<https://devfeed.tech/tags/multimodal-ai.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [research](<https://devfeed.tech/tags/research.md>), [training](<https://devfeed.tech/tags/training.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vqa](<https://devfeed.tech/tags/vqa.md>)

## AI overview

Visual Salamandra is a multilingual multimodal model built by extending the Salamandra Instructed 7B model with Google's SigLIP image encoder, an MLP projector, and late-fusion techniques. It processes text, images, and videos, with training focused on visual grounding, document understanding, mathematical reasoning, OCR, and European-language coverage.

## Source excerpt

A Blog post by Language Technologies Laboratory @ Barcelona Supercomputing Center on Hugging Face