Add library_name to metadata

README.md

@@ -1,15 +1,16 @@
 ---
-license: apache-2.0
-datasets:
-- Moreza009/AAV_datasets
 base_model:
 - nferruz/ProtGPT2
+datasets:
+- Moreza009/AAV_datasets
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 tags:
 - biology
 - protein
 - medicine
 - capsid_engineering
-pipeline_tag: text-generation
 ---
 
 <h1 align="center">AAVGen: Precision Engineering of Adeno-associated Virus for Renal Selective Targeting</h1>
@@ -24,7 +25,7 @@ pipeline_tag: text-generation
     <img src="https://img.shields.io/badge/python-3.8+-blue.svg" alt="Python 3.8+">
   </a>
   <a href="https://github.com/mohammad-gh009/AAVGen">
-    <img src="https://img.shields.io/badge/GitHub-Code-blue.svg?logo=githu" alt="Github">
+    <img src="https://img.shields.io/badge/GitHub-Code-blue.svg?logo=github" alt="Github">
   </a>
   <a href="https://arxiv.org/abs/2602.18915">
     <img src="https://img.shields.io/badge/arXiv-2602.18915-b31b1b.svg" alt="arXive">
@@ -61,7 +62,9 @@ AAVGen is a generative protein language model designed for precision engineering
 ### Model Sources
 
 - **Repository:** [Moreza009/AAVGen](https://huggingface.co/Moreza009/AAVGen)
+- **Code:** [GitHub](https://github.com/mohammad-gh009/AAVGen)
 - **Dataset:** [Moreza009/AAV_datasets](https://huggingface.co/datasets/Moreza009/AAV_datasets)
+- **Paper:** [arXiv:2602.18915](https://arxiv.org/abs/2602.18915)
 
 ---
 
@@ -69,7 +72,8 @@ AAVGen is a generative protein language model designed for precision engineering
 
 ### Direct Use
 
-AAVGen can be used to generate novel AAV capsid protein sequences (VP1) by providing a start token (`<|endoftext|>\nM`). The generated sequences are intended for in silico screening, functional evaluation, and downstream experimental validation in AAV-based gene therapy development. The model is particularly suited for generating capsid variants optimized for renal tropism, high production fitness, and thermal stability.
+AAVGen can be used to generate novel AAV capsid protein sequences (VP1) by providing a start token (`<|endoftext|>
+M`). The generated sequences are intended for in silico screening, functional evaluation, and downstream experimental validation in AAV-based gene therapy development. The model is particularly suited for generating capsid variants optimized for renal tropism, high production fitness, and thermal stability.
 
 ### Downstream Use
 
@@ -116,7 +120,8 @@ model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
 model.eval()
 
 # Generate AAV capsid sequences
-prompt = tokenizer.eos_token + "\n" + "M"
+prompt = tokenizer.eos_token + "
+" + "M"
 inputs = tokenizer(prompt, return_tensors="pt").to(device)
 
 with torch.no_grad():