Update README.md

README.md

@@ -174,27 +174,30 @@ Example with simulated OCR noise:
 ```python
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-tokenizer = AutoTokenizer.from_pretrained("impresso-project/nel-hipe-multilingual")
-model = AutoModelForSeq2SeqLM.from_pretrained("impresso-project/nel-hipe-multilingual").eval()
+NEL_MODEL_NAME = "impresso-project/nel-mgenre-multilingual"
+
+# Load the tokenizer and model from the specified pre-trained model name
+# The model used here is "https://huggingface.co/impresso-project/nel-mgenre-multilingual"
+nel_tokenizer = AutoTokenizer.from_pretrained("impresso-project/nel-mgenre-multilingual")
 
 sentences = ["[START] Un1ted Press [END] - On the h0me fr0nt, the British p0pulace remains steadfast in the f4ce of 0ngoing air raids.",
              "In [START] Lon6on [END], trotz d3r Zerstörung, ist der Geist der M3nschen ungeb4ochen, mit Freiwilligen und zivilen Verteidigungseinheiten, die unermüdlich arbeiten, um die Kriegsanstrengungen zu unterstützen.",
              "Les rapports des correspondants de la [START] AFP [END] mettent en lumiére la poussée nationale pour augmenter la production dans les usines, essentielle pour fournir au front les matériaux nécessaires à la victoire."]
 
+nel_pipeline = pipeline("generic-nel", model=NEL_MODEL_NAME, 
+                        tokenizer=nel_tokenizer, 
+                        trust_remote_code=True,
+                        device='cpu')
 for sentence in sentences:
-    outputs = model.generate(
-        **tokenizer([sentence], return_tensors="pt"),
-        num_beams=5,
-        num_return_sequences=5
-    )
-    
-    print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
+    print(sentence)
+    linked_entity = nel_pipeline(sentence)
+    print(linked_entity)
 ```
 
 ```
-['United Press International >> en ', 'Un1ted Press >> en ', 'Joseph Bradley Varnum >> en ', 'The Press >> en ', 'The Unused Press >> en ']
-['London >> de ', 'Longbourne >> de ', 'Longbon >> de ', 'Longston >> de ', 'Lyon >> de ']
-['Agence France-Presse >> fr ', 'Agence France-Presse >> fr ', 'Agence France-Presse de la Presse écrite >> fr ', 'Agence France-Presse de la porte de Vincennes >> fr ', 'Agence France-Presse de la porte océanique >> fr ']
+[{'title': 'United Press International', 'qid': 'Q493845', 'url': 'https://en.wikipedia.org/wiki/United_Press_International'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}, {'title': 'Joseph Bradley Varnum', 'qid': 'Q1706673', 'url': 'https://en.wikipedia.org/wiki/Joseph_Bradley_Varnum'}, {'title': 'The Press', 'qid': 'Q2413590', 'url': 'https://en.wikipedia.org/wiki/The_Press'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}]
+[{'title': 'London', 'qid': 'Q84', 'url': 'https://en.wikipedia.org/wiki/London'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}, {'title': 'Lyon', 'qid': 'Q456', 'url': 'https://en.wikipedia.org/wiki/Lyon'}]
+[{'title': 'Agence France-Presse', 'qid': 'Q40464', 'url': 'https://en.wikipedia.org/wiki/Agence_France-Presse'}, {'title': 'Agence France-Presse', 'qid': 'Q40464', 'url': 'https://en.wikipedia.org/wiki/Agence_France-Presse'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}, {'title': 'NIL', 'qid': 'NIL', 'url': 'None'}]
 ```
 
 ---