OpenGVLab
/

HoVLE-HD

Image-Text-to-Text

feature-extraction

vision-language model

Model card Files Files and versions Community

taochenxin commited on Dec 23, 2024

Commit

4981258

·

verified ·

1 Parent(s): 5b0921e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ We introduce **HoVLE**, a novel monolithic vision-language model (VLM) that proc
 HoVLE significantly surpasses previous monolithic VLMs and demonstrates competitive performance with compositional VLMs. This work narrows the gap between monolithic and compositional VLMs, providing a promising direction for the development of monolithic VLMs.
-This repository releases the HoVLE-HD model with 2.6B parameters. It is built upon [internlm2-chat-1_8b](https://huggingface.co/internlm/internlm2-chat-1_8b). By adopting high-definition images, HoVLE-HD demonstrates superior performance, especially on visual-question answering benchmarks. Please refer to [HoVLE](https://huggingface.co/taochenxin/HoVLE) for the standard version. For more details, please refer to our [paper]().
 ## Model Details

 HoVLE significantly surpasses previous monolithic VLMs and demonstrates competitive performance with compositional VLMs. This work narrows the gap between monolithic and compositional VLMs, providing a promising direction for the development of monolithic VLMs.
+This repository releases the HoVLE-HD model with 2.6B parameters. It is built upon [internlm2-chat-1_8b](https://huggingface.co/internlm/internlm2-chat-1_8b). By adopting high-definition images, HoVLE-HD demonstrates superior performance, especially on visual-question answering benchmarks. Please refer to [HoVLE](https://huggingface.co/OpenGVLab/HoVLE) for the standard version. For more details, please refer to our [paper]().
 ## Model Details