Add pipeline tag, link to paper
Browse filesThis PR ensures the model can be viewed from https://huggingface.co/models?pipeline_tag=image-text-to-text and is linked to https://huggingface.co/papers/2406.11823.
README.md
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-text-to-text
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
This repository contains the Elva-LLaMa-160M model presented in [On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning](https://huggingface.co/papers/2406.11823).
|