Dataset · lmms-lab-encoder
Evaluation dataset for MME benchmark
lmms-lab-encoder/MME
Multimodal image-text dataset for testing vision-language models (VLMs).
What's inside
This dataset serves as an evaluation split for the MME benchmark and includes between 1 and 10 thousand text and image examples. The language and detailed column structure are not specified in the card.
What you can do with it
- Evaluate basic visual recognition and analysis capabilities of vision-language models (VLMs)
- Perform regression testing on multimodal models after fine-tuning
- Size
- 1K–10K rows
- Downloads this month
- 25.6K
- Likes
- 37
How to load it
from datasets import load_dataset
ds = load_dataset("lmms-lab-encoder/MME")