Add relevant metadata, link to Github repository and specify license.

This PR improves the model card by adding the relevant `library_name` (Transformers) and `pipeline_tag` (text-generation) so people can find the model at https://huggingface.co/models?pipeline_tag=text-generation.

It also includes a link to the Github repository, and specifies the license as Apache 2.0.

README.md

@@ -1,3 +1,11 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+license: apache-2.0
+---
+
 This is a 800M parameters model pre-trained with [QuEST](https://arxiv.org/abs/2502.05003) over 80B C4 tokens in 2:4 sparse INT4 format.
 
-The code to verify that this model works in INT4 can be found [here](https://github.com/IST-DASLab/QuEST/blob/main/src/HadamardFourEightTesting.ipynb).
+The code to verify that this model works in INT4 can be found [here](https://github.com/IST-DASLab/QuEST/blob/main/src/HadamardFourEightTesting.ipynb).
+
+Github repository: https://github.com/IST-DASLab/QuEST