message

app.py

@@ -30,38 +30,11 @@ for i in range(0, 20):
 
 def get_score(abstract):
 
-    model = AutoModelForSequenceClassification.from_pretrained("arianasutanto/finetuned-distilbert")
-    tokenizer = AutoTokenizer.from_pretrained("arianasutanto/finetuned-distilbert", pad_to_max_length=True)
-
-    inputs = tokenizer(abstract, padding='max_length', truncation=True, return_tensors='pt')
-
-    with torch.no_grad():
-        logits = model(**inputs).logits
-        print(logits)
-
-
-    outputs = model(inputs['input_ids'], attention_mask=inputs['attention_mask'])
-    scores = torch.softmax(outputs.logits, dim=1)[0]
-    print(scores)
-    probs = F.softmax(scores, dim=0)
-    print(probs)
-    accept_prob = probs[0].item()
-
-    print(accept_prob)
-
-    #return #accept_prob
-
-    #score = F.softmax(outputs.logits, dim=1)
-    #print(score)
-    
-    ##accept_prob = probs[0].item()
-    #model_name = "arianasutanto/finetuned-distilbert"
-
-    #classifier = pipeline("text-classification", model=model_name)
-    #result = classifier(abstract)
+    model_name = "arianasutanto/finetuned-distilbert"
+    classifier = pipeline("text-classification", model=model_name)
+    result = classifier(abstract)
    
-
-    return logits
+    return result
 
 
 
@@ -74,8 +47,4 @@ if st.button("Submit"):
    st.write(predictability)
 
 
-#abstract = abstracts[patent_num]
-#st.write(abstract)
-#claim = claims[patent_num]
-#st.write(claim)