---
license: apache-2.0
language:
- en
library_name: keras
tags:
- SkimLit
- NLP
- Abstract Classification
---
  # SkimLit Model                                                  
                                                                   
  Keras model for classifying scientific abstract sections         
  (Background, Objective, Methods, Results, Conclusions).
                                                                   
  ## Usage                                                         
   
  ```python                                                        
  import tensorflow as tf
  model = tf.keras.models.load_model('model_5.keras')              
                                                                   
  Model Details                                                    
                                                                   
  - Framework: TensorFlow/Keras                                    
  - Input: Token embeddings + character text + positional info
  - Output: 5 classes (Background, Objective, Methods, Results,    
  Conclusions)                                                     
                                                                   
  **Metadata à remplir:**                                          
  - **license**: `apache-2.0` (ou autre)                           
  - **language**: `English`                                        
  - **tags**: `skimlit`, `nlp`, `text-classification`              
  - **pipeline_tag**: `text-classification`