lmms-lab
Organization Account
This organization is currently unclaimed.

If you represent this organization, we went ahead and indexed your public data. Just let us know, we're waiting to hand over control.

lmms-lab's Repositories
Displaying Page 1 of 3 (26 total Repositories)

OCRBench is a comprehensive evaluation benchmark designed to assess the OCR capabilities of Large Multimodal Models. It comprises five components: Text Recognition, SceneText-Centric VQA, Document-Oriented VQA, Key Information Extraction, and Handwritten Mathematical Expression Recognition. The benchmark includes 1000 question-answer pairs, and all the answers undergo manual verification and correction to ensure a more precise evaluation.

4.5 gb
10K23
Updated: 2 months ago
public
0

3 gb
45K131
Updated: 2 months ago
public
0

29.8 mb
1418K1
Updated: 2 months ago
public
0

1.6 gb
121K45
Updated: 2 months ago

476.5 mb
127.7K
Updated: 4 months ago
public
0

3.4 gb
12K2
Updated: 5 months ago

15.6 mb
21601
Updated: 10 months ago

74.5 mb
21500
Updated: 10 months ago
public
0

405.9 kB
12
Updated: 10 months ago
public
0

793.1 mb
235K5
Updated: 11 months ago