Update app.py

app.py

@@ -21,6 +21,46 @@ model = AutoModelForSeq2SeqLM.from_pretrained(nombre_modelo)
 tokenizer = AutoTokenizer.from_pretrained(nombre_modelo)
 
 
+
+
+
+import numpy as np
+
+import evaluate
+
+metric = evaluate.load("sacrebleu")
+
+def postprocess_text(preds, labels):
+    preds = [pred.strip() for pred in preds]
+    labels = [[label.strip()] for label in labels]
+
+    return preds, labels
+
+def compute_metrics(eval_preds):
+    preds, labels = eval_preds
+    if isinstance(preds, tuple):
+        preds = preds[0]
+    decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)
+
+    labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
+    decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)
+
+    decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)
+
+    result = metric.compute(predictions=decoded_preds, references=decoded_labels) 
+    result = {"bleu": result["score"]}
+
+    prediction_lens = [np.count_nonzero(pred != tokenizer.pad_token_id) for pred in preds]
+    result["gen_len"] = np.mean(prediction_lens)
+    result = {k: round(v, 4) for k, v in result.items()}
+    return result
+
+
+
+
+#CAMBIAR LO QUE SE RETORNA Y PONER LO DEL DECODER.
+
+
 def predict(frase):
     #img = PILImage.create(img)
     inputs = tokenizer(frase, return_tensors="pt")