Add library_name and link to Github repo

This PR improves the model card by adding the `library_name` metadata and linking to the Github repository.

README.md

@@ -1,5 +1,6 @@
 ---
-license: apache-2.0
+base_model:
+- meta-llama/Llama-3.1-8B
 datasets:
 - HiTZ/GuideX_pre-training_data
 - ACE05
@@ -12,10 +13,9 @@ datasets:
 - wnut_17
 language:
 - en
+license: apache-2.0
 metrics:
 - f1
-base_model:
-- meta-llama/Llama-3.1-8B
 tags:
 - code
 - text-generation-inference
@@ -25,12 +25,12 @@ tags:
 - Event Extraction
 - Relation Extraction
 - LLaMA
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 <p align=
 
-
-
 # Model Card for GuideX-8B
 
 <p align="center">
@@ -46,8 +46,8 @@ tags:
 This model achieves state-of-the-art performance on zero-shot Named Entity Recognition (NER) by first training on `GuideX`, a large-scale synthetic dataset with executable guidelines, and then fine-tuning on a collection of gold-standard IE datasets.
 
 -   **Homepage:** [https://neilus03.github.io/guidex.com/](https://neilus03.github.io/guidex.com/)
--   **Paper:** [GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction](https://arxiv.org/abs/2506.00649)
--   **Code & Data:** The code and data for reproducing the GuideX methodology are available on the project homepage.
+-   **Paper:** [GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction](https://huggingface.co/papers/2506.00649)
+-   **Code & Data:** The code and data for reproducing the GuideX methodology are available on the project homepage and on [Github](https://github.com/HiTZ/GUIDEX).
 
 ## Model Description
 
@@ -56,5 +56,4 @@ This model achieves state-of-the-art performance on zero-shot Named Entity Recog
 -   **Model type:** Decoder-only Transformer (Text Generation)
 -   **Language(s):** English
 -   **License:** Llama 2 Community License
--   **Finetuned from model:** `meta-llama/Llama-3.1-8B`
-
+-   **Finetuned from model:** `meta-llama/Llama-3.1-8B`