Improve model card: Add `library_name` and GitHub link

This PR improves the model card by:
- Adding the `library_name: transformers` to the metadata, which enables the "How to Use" widget on the model page and indicates compatibility with the Transformers library.
- Adding a direct link to the primary paper on Hugging Face.
- Adding a clear link to the GitHub repository in the main content for easier access to the code.

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - transformer
 - causal-lm
@@ -7,11 +8,14 @@ tags:
 - constructive-learning
 - frozen-embeddings
 - bvv
-pipeline_tag: text-generation
+library_name: transformers
 ---
 
 # Model Card for abs-bvv-3
 
+This model is presented in the paper [Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate](https://huggingface.co/papers/2507.07129).
+The official code repository can be found at: [https://github.com/Bochkov/BVV241-tokenizers](https://github.com/Bochkov/BVV241-tokenizers).
+
 ## Model Description
 
 `abs-bvv-3` is a 1.7 billion parameter decoder-only Transformer model. It is the 3th model in the **Progressive Growth Transformers (PGT)** series, designed to explore how linguistic and reasoning capabilities emerge as a function of model depth.
@@ -103,4 +107,5 @@ outputs = model.generate(
     do_sample=True
 )
 
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```