Task
Image Text To Text
D
deepseek-ai/deepseek-vl2-tiny
Image Text To Text·deepseek-ai· 910.7K· 248
transformers
other
3.4B params
arxiv:2412.10302license:otherregion:us
Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is
# pull & run locally
pip install mlforge-sdk && mlforge pull deepseek-ai/deepseek-vl2-tiny
pip install mlforge-sdk && mlforge pull deepseek-ai/deepseek-vl2-tiny
Model details
Provider
deepseek-ai
Framework
transformers
Parameters
3.4B
Size
6.3 GB
License
other
Downloads
910.7K
Likes
248
Paper
arXiv:2412.10302
Updated
2024-12-18
About deepseek-ai/deepseek-vl2-tiny
Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models.