Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 9.71M • 1.6k
DocRAG Baseline Models
Baseline VLMs used in DocRAG for either retrieval or generation.
-
-
Qwen/Qwen2.5-VL-7B-Instruct-AWQ
Image-Text-to-Text • 8B • Updated • 1.42M • 106 -
Metric-AI/ColQwen2.5-7b-multilingual-v1.0
Visual Document Retrieval • Updated • 11 • 16 -
Metric-AI/ColQwen2.5-3b-multilingual-v1.0
Visual Document Retrieval • Updated • 671 • 9 -
google/paligemma2-3b-pt-448
Image-Text-to-Text • 3B • Updated • 57.7k • 50 -
OpenGVLab/InternVL3-2B
Image-Text-to-Text • 2B • Updated • 51.7k • 46 -
OpenGVLab/InternVL3-8B
Image-Text-to-Text • 8B • Updated • 70.7k • 106 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 1.71M • 678 -
google/siglip2-base-patch16-512
Zero-Shot Image Classification • 0.4B • Updated • 124k • 47 -
nomic-ai/colnomic-embed-multimodal-3b
Visual Document Retrieval • Updated • 11.8k • 39 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval • Updated • 78.7k • 99