Improve model card: Add pipeline tag, library name, update license, and link to code

This PR enhances the model card for `Tucan-27B-v1.0-LoRA` by:
- Adding `pipeline_tag: text-generation` to the metadata, ensuring the model is discoverable via the pipeline filter on the Hub.
- Adding `library_name: transformers` to the metadata, which will enable the "how to use" button and provide relevant code snippets for users.
- Updating the `license` tag in the metadata to `cc-by-4.0` to accurately reflect the license declared within the model card's content itself.
- Adding a direct link to the model's GitHub repository: `https://github.com/llm-bg/tucan`.
- Including the Hugging Face paper page link for comprehensive documentation, while retaining the existing arXiv link for completeness.

README.md

@@ -1,20 +1,24 @@
 ---
-license: gemma
-language:
-- bg
 base_model:
 - INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0
+language:
+- bg
+license: cc-by-4.0
 tags:
 - function_calling
 - MCP
 - tool_use
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 # Tucan-27B-v1.0-LoRA
 
 ## Bulgarian Language Models for Function Calling 🇧🇬
 
-**Paper: https://arxiv.org/abs/2506.23394**
+**Paper: [Teaching a Language Model to Speak the Language of Tools](https://huggingface.co/papers/2506.23394)**
+arXiv: https://arxiv.org/abs/2506.23394
+Code: https://github.com/llm-bg/tucan
 
 ## Overview 🚀
 
@@ -113,7 +117,12 @@ def create_prompt(functions, user_query):
 """
     
     functions_text = json.dumps(functions, ensure_ascii=False, indent=2)
-    full_prompt = f"{system_prompt}\n## Налични функции:\n{functions_text}\n\n## Потребителска заявка:\n{user_query}"
+    full_prompt = f"{system_prompt}
+## Налични функции:
+{functions_text}
+
+## Потребителска заявка:
+{user_query}"
     
     chat = [{"role": "user", "content": full_prompt}]
     return tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)