OpenGVLab
/

InternVL-Chat-V1-2-Plus

Image-Text-to-Text

feature-extraction

Model card Files Files and versions Metrics Training metrics Community

czczup commited on Feb 21

Commit

2aae8fa

•

1 Parent(s): 5ccea55

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ datasets:
 \[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\] \[[Chat Demo](https://internvl.opengvlab.com/)\]
-InternVL-Chat-V1.2-Plus uses the same model architecture as [InternVL-Chat-V1.2](https://huggingface.co/OpenGVLab/InternVL-Chat-Chinese-V1-2), but the difference lies in the SFT dataset: while InternVL-Chat-V1.2 only utilizes an SFT dataset with 1.2M samples, our Plus version employs an SFT dataset with 12M samples.
 <img width="600" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/GIEKCvNc1Y5iMQqLv645p.png">

 \[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\] \[[Chat Demo](https://internvl.opengvlab.com/)\]
+InternVL-Chat-V1.2-Plus uses the same model architecture as [InternVL-Chat-V1.2](https://huggingface.co/OpenGVLab/InternVL-Chat-Chinese-V1-2), but the difference lies in the SFT dataset. InternVL-Chat-V1.2 only utilizes an SFT dataset with 1.2M samples, while our plus version employs an SFT dataset with 12M samples.
 <img width="600" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/GIEKCvNc1Y5iMQqLv645p.png">