Update app.py

Change number of labels

app.py

@@ -1,31 +1,31 @@
-import streamlit as st
-import pandas as pd
-import numpy as np
-from transformers import (AutoTokenizer, AutoModelForSequenceClassification)
-
-model = AutoModelForSequenceClassification.from_pretrained('tiedaar/metacognitive-cls',
-                                                           num_labels=8,
-                                                           problem_type = "multi_label_classification")
-tokenizer = AutoTokenizer.from_pretrained('tiedaar/metacognitive-cls', use_fast=False)
-
-labels = list(model.config.id2label.values())
-
-def sigmoid(x):
-   return 1/(1 + np.exp(-x))
-    
-def generate_output(sequence):
-    input_ids = tokenizer(sequence, return_tensors='pt')['input_ids']
-    outputs = np.array(model(input_ids).logits.detach().reshape(-1))
-    predictions = sigmoid(outputs)
-    predictions = (predictions > 0.5).astype(int)
-    return predictions
-
-st.title("Metacognitive Strategy Classification")
-st.subheader("This app classifies natural language descriptions of study strategies according to the metacognitive strategies being employed")
-
-sequence = st.text_area("Please input the text here")
-df = pd.DataFrame(columns=labels)
-if st.button("Click here"):
-    resp = generate_output(sequence)
-    df.loc[len(df)] = resp
+import streamlit as st
+import pandas as pd
+import numpy as np
+from transformers import (AutoTokenizer, AutoModelForSequenceClassification)
+
+model = AutoModelForSequenceClassification.from_pretrained('tiedaar/metacognitive-cls',
+                                                           num_labels=10,
+                                                           problem_type = "multi_label_classification")
+tokenizer = AutoTokenizer.from_pretrained('tiedaar/metacognitive-cls', use_fast=False)
+
+labels = list(model.config.id2label.values())
+
+def sigmoid(x):
+   return 1/(1 + np.exp(-x))
+    
+def generate_output(sequence):
+    input_ids = tokenizer(sequence, return_tensors='pt')['input_ids']
+    outputs = np.array(model(input_ids).logits.detach().reshape(-1))
+    predictions = sigmoid(outputs)
+    predictions = (predictions > 0.5).astype(int)
+    return predictions
+
+st.title("Metacognitive Strategy Classification")
+st.subheader("This app classifies natural language descriptions of study strategies according to the metacognitive strategies being employed")
+
+sequence = st.text_area("Please input the text here")
+df = pd.DataFrame(columns=labels)
+if st.button("Click here"):
+    resp = generate_output(sequence)
+    df.loc[len(df)] = resp
     st.table(df)