Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 4.36M • • 1.49k
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 • 304k • 99 -
Metric-AI/ColQwen2.5-7b-multilingual-v1.0
Visual Document Retrieval • Updated • 21k • 16 -
Metric-AI/ColQwen2.5-3b-multilingual-v1.0
Visual Document Retrieval • Updated • 1.43k • 9 -
google/paligemma2-3b-pt-448
Image-Text-to-Text • 3B • Updated • 45.9k • 47 -
OpenGVLab/InternVL3-2B
Image-Text-to-Text • Updated • 39.8k • 45 -
OpenGVLab/InternVL3-8B
Image-Text-to-Text • Updated • 124k • 103 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 2.01M • 667 -
google/siglip2-base-patch16-512
Zero-Shot Image Classification • 0.4B • Updated • 147k • 37 -
nomic-ai/colnomic-embed-multimodal-3b
Visual Document Retrieval • Updated • 1.77k • 37 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval • Updated • 74.8k • 98