Update app.py

app.py

@@ -134,8 +134,8 @@ def main():
                outputs = qa_model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])
                answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0])
                answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])
-               answer_start_scores = tf.nn.softmax(outputs.start_logits)
-               answer_end_scores = tf.nn.softmax(outputs.end_logits)
+               #answer_start_scores = tf.nn.softmax(outputs.start_logits)
+               #answer_end_scores = tf.nn.softmax(outputs.end_logits)
                predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1] 
                answer=tokenizer.decode(predict_answer_tokens) 
 
@@ -144,9 +144,9 @@ def main():
                    # Extract 5 greatest values fo start and end scores with indeces
                    #answer_start_scores= tf.math.top_k(answer_start_scores, k=5)
                    #answer_end_scores= tf.math.top_k(answer_end_scores, k=5)
-                   score = answer_start_scores[0]*answer_end_scores[0]
-                   st.write(f'Aqui {answer}' )
-                   st.write(score)
+                   #score = answer_start_scores[0]*answer_end_scores[0]
+                   #st.write(f'Aqui {answer}' )
+                   #st.write(score)
                    cantidad_respuestas = cantidad_respuestas + 1
                    df_answer.loc[i, "answer"] = answer
                    lista_noticias_respuestas.append(df_answer.loc[i].to_frame().T)