Visual Salamandra: Pushing the Boundaries of Multimodal Understanding

Visual Salamandra extends the Salamandra 7B LLM to images and video via Google's SigLIP encoder and late-fusion, enabling vision-language alignment. It uses a four-phase training pipeline (projector pre-training, high-quality vision pretraining, instruction tuning, full multimodal tuning) with 6.1M instructions, prioritizing multilingual European data.

Source

HuggingFace Blog

Ingéré

11 AVR. 2025 · 19:10

Score édito

4.0 / 5