Add model card
Browse filesThis PR adds a model card for the NativeRes-LLaVA model introduced in [Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models](https://huggingface.co/papers/2506.12776).
It adds a link to the paper page, the pipeline tag `image-feature-extraction`, the library name `transformers`, and a link to the project page.
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: image-feature-extraction
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This repository contains the NativeRes-LLaVA model from [Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models](https://huggingface.co/papers/2506.12776).
|
| 8 |
+
|
| 9 |
+
Project page: https://niujunbo2002.github.io/NativeRes-LLaVA/
|
| 10 |
+
|
| 11 |
+
For code, see https://github.com/Niujunbo2002/NativeRes-LLaVA.
|