Processed ("Unified") datasets used in DocRAG for training or inference purposes.
AHS
AHS-uni
AI & ML interests
None yet
Organizations
None yet
Baseline VLMs used in DocRAG for either retrieval or generation.
-
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 2.55M • • 1.41k -
Qwen/Qwen2.5-VL-7B-Instruct-AWQ
Image-Text-to-Text • 8B • Updated • 95.9k • 96 -
Metric-AI/ColQwen2.5-7b-multilingual-v1.0
Visual Document Retrieval • Updated • 1.34k • 15 -
Metric-AI/ColQwen2.5-3b-multilingual-v1.0
Visual Document Retrieval • Updated • 718 • 9
Processed ("Unified") datasets used in DocRAG for training or inference purposes.
Samples of the datasets used in DocRAG
Baseline VLMs used in DocRAG for either retrieval or generation.
-
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 2.55M • • 1.41k -
Qwen/Qwen2.5-VL-7B-Instruct-AWQ
Image-Text-to-Text • 8B • Updated • 95.9k • 96 -
Metric-AI/ColQwen2.5-7b-multilingual-v1.0
Visual Document Retrieval • Updated • 1.34k • 15 -
Metric-AI/ColQwen2.5-3b-multilingual-v1.0
Visual Document Retrieval • Updated • 718 • 9