Shijian Wang
shijianS01
AI & ML interests
Data-Centric AI, Large Multimodal Models
Recent Activity
updated
a dataset
12 days ago
shijianS01/OCR-VQA
published
a dataset
12 days ago
shijianS01/OCR-VQA
published
a model
12 days ago
shijianS01/OCR-VQA
Organizations
None yet
Collections
2
Models and Datasets for TemplateMatters
-
shijianS01/llava-v1.5-13b-lora-100-templated
Image-Text-to-Text • Updated • 5 -
shijianS01/llava-v1.5-13b-lora-10k-templated
Image-Text-to-Text • Updated • 6 -
shijianS01/llava-v1.5-13b-lora-15k-templated
Image-Text-to-Text • Updated • 8 -
shijianS01/llava-v1.5-13b-lora-1k-templated
Image-Text-to-Text • Updated • 7
Papers
2
models
13
shijianS01/OCR-VQA
Updated
shijianS01/ocr_vqa
Updated
shijianS01/llava-v1.5-13b-lora-15k-templated
Image-Text-to-Text
•
Updated
•
8
shijianS01/llava-v1.5-13b-lora-5k-templated
Image-Text-to-Text
•
Updated
•
7
shijianS01/llava-v1.5-13b-lora-10k-templated
Image-Text-to-Text
•
Updated
•
6
shijianS01/llava-v1.5-13b-lora-1k-templated
Image-Text-to-Text
•
Updated
•
7
shijianS01/llava-v1.5-13b-lora-100-templated
Image-Text-to-Text
•
Updated
•
5
shijianS01/llava-v1.5-7b-lora-10k-templated
Image-Text-to-Text
•
Updated
•
5
shijianS01/llava-v1.5-7b-lora-100-templated
Image-Text-to-Text
•
Updated
•
6
shijianS01/llava-v1.5-7b-lora-5k-templated
Image-Text-to-Text
•
Updated
•
6
datasets
6
shijianS01/OCR-VQA
Viewer
•
Updated
•
208k
•
85
shijianS01/mmmu-subset
Viewer
•
Updated
•
100
•
76
shijianS01/tma-subset
Viewer
•
Updated
•
100
•
77
shijianS01/seedbench-subset
Viewer
•
Updated
•
100
•
84
shijianS01/mmbench-subset
Viewer
•
Updated
•
100
•
83
shijianS01/blink-subset
Viewer
•
Updated
•
100
•
140