Add pipeline tag, library name, link to project page and github URL

This PR improves the model card, by:
- adding a relevant pipeline tag, ensuring people can find the model at https://huggingface.co/models?pipeline_tag=text-generation, as well as the `library_name`.
- adding a link to the Github repository, enabling people to easier find the code.
- adding a link to the project page.

README.md

@@ -1,5 +1,7 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 The *TokenFormer* is a **fully attention-based architecture** 
@@ -10,6 +12,10 @@ It contains four models of sizes
 All 4 model sizes are trained on the exact 
 same data, in the exact same order.
 
+Code: https://github.com/Haiyang-W/TokenFormer
+
+Project page: https://haiyang-w.github.io/tokenformer.github.io/
+
 # TokenFormer-450M
 
 ## Model Details
@@ -92,4 +98,4 @@ TokenFormer compared with Opensource Transformer-based LLMs.
 | Pythia       |    2.8B  | 64.7     |     59.3  | 74.0 |  64.1  | 32.9  |  59.7      |   59.1   | 
 | **TokenFormer**  |    1.5B  | **64.7**     |     60.0  | **74.8** |  **64.8**  | 32.0  |  59.7      |   **59.3**   |
 <figcaption>Zero-shot evaluation of Language Modeling. </figcaption>
-</figure>
+</figure>