Improve model card: Add Github link, and update pipeline tag

This PR adds:

- A Github link, so people can find your code.
- A `pipeline_tag`, ensuring people can find your model at https://huggingface.co/models?pipeline_tag=image-text-to-text.

README.md

@@ -1,13 +1,13 @@
 ---
-license: apache-2.0
+base_model:
+- zhumj34/Mipha-3B
 datasets:
 - liuhaotian/LLaVA-Instruct-150K
 language:
 - en
-base_model:
-- zhumj34/Mipha-3B
-pipeline_tag: image-text-to-text
 library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
 tags:
 - transformers
 - llm
@@ -15,9 +15,10 @@ tags:
 - conversational
 - olympus
 - llava
-- text-generation
+- image-text-to-text
 - vision-language
 ---
+
 <p align="center">
   <img src="https://github.com/yuanze-lin/Olympus/blob/main/asset/olympus.png?raw=true" alt="icon" width="150" height="150" style="vertical-align:middle; margin-right:5px;" />
 </p>
@@ -162,6 +163,8 @@ bash scripts/mipha/eval/vqav2.sh
   <img src="https://github.com/yuanze-lin/Olympus/blob/main/asset/application.png?raw=true" alt="Capacity" width="1000" height="100"/>
 </p>
 
+You can find the code repository at: https://github.com/yuanze-lin/Olympus
+
 ## Citation
 
 If you find Olympus useful for your research and applications, please cite using this BibTeX: