Update app.py

app.py

@@ -44,33 +44,54 @@ class TransformerChatbot(Model):
 st.title("UniGLM TEXT completion Model")
 st.subheader("Next Word Prediction AI Model by Webraft-AI")
 #Picking what NLP task you want to do
-option = st.selectbox('Model',('13M_OLD','26M_OLD')) #option is stored in this variable
+option = st.selectbox('Model',('1','2')) #option is stored in this variable
 #Textbox for text user is entering
 st.subheader("Enter a word from which a sentence / word would be predicted")
-
 text2 = st.text_input('Enter word: ') #text is stored in this variable
 
-
-if option == '13M_OLD':
-    option2 = st.selectbox('Type',('word','sentence'))
-    if option2 == 'word':
-        len2 = 1
-    else:
-        len2 = 13
+if option == '1':
+    with open("data2.txt","r") as f:
+        text = f.read()
+    text = text.lower()
+    words = text.split()
+    loaded_dict = np.load("dict_predict3.bin.npz", allow_pickle=True)
+    word_to_num = loaded_dict["word_to_num"].item()
+    num_to_word = loaded_dict["num_to_word"].item()
+    X = []
+    X.append(word_to_num[words[-1]])
+    X_train = pad_sequences([X])
+    y_train = pad_sequences([Y])
     vocab_size = 100000
     max_len = 1
     d_model = 64  # 64 , 1024
     n_head = 4  # 8 , 16
     ff_dim = 256  # 256 , 2048
     dropout_rate = 0.1  # 0.5 , 0.2
-    weights = "predict3"
-    datafile = "data2.txt"
-    dict = "dict_predict3.bin.npz"
-    with open(datafile,"r") as f:
+
+
+    chatbot = TransformerChatbot(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate)
+    chatbot.load_weights("predict3")
+    chatbot.build(input_shape=(None, max_len)) # Build the model
+    chatbot.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
+    
+        given_X1 = other_num1
+        input_sequence1 = pad_sequences([given_X1], maxlen=max_len, padding='post')
+        output_sentence = ""
+        for _ in range(1):
+            predicted_token = np.argmax(chatbot.predict(input_sequence1), axis=-1)
+            predicted_token = predicted_token.item()
+            out = num_to_word[predicted_token]
+            input_sequence1 = pad_sequences([given_X1], maxlen=max_len, padding='post')
+
+        out2 = output_sentence
+        
+    
+else:
+    with open("data2.txt","r") as f:
         text = f.read()
     text = text.lower()
     words = text.split()
-    loaded_dict = np.load(dict, allow_pickle=True)
+    loaded_dict = np.load("dict_predict3.bin.npz", allow_pickle=True)
     word_to_num = loaded_dict["word_to_num"].item()
     num_to_word = loaded_dict["num_to_word"].item()
     X = []
@@ -85,48 +106,46 @@ if option == '13M_OLD':
     X.append(word_to_num[words[-1]])
     X_train = pad_sequences([X])
     y_train = pad_sequences([Y])
-    
+    vocab_size = 100000
+    max_len = 1
+    d_model = 64  # 64 , 1024
+    n_head = 4  # 8 , 16
+    ff_dim = 256  # 256 , 2048
+    dropout_rate = 0.1  # 0.5 , 0.2
 
 
     chatbot = TransformerChatbot(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate)
-    chatbot.load_weights(weights)
+    chatbot.load_weights("predict3")
     chatbot.build(input_shape=(None, max_len)) # Build the model
     chatbot.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
-    chatbot.fit(X_train, y_train, epochs=1, batch_size=64)
+    
     for i in range(1):
-        other_text2 = text2
-        other_text2 = other_text2.lower()
-        other_words2 = other_text2.split()
-        other_num2 = [word_to_num[word] for word in other_words2]
-        given_X2 = other_num2
-        input_sequence2 = pad_sequences([given_X2], maxlen=max_len, padding='post')
-        output_sentence = other_text2 + ""
-        for _ in range(len2):
-            predicted_token = np.argmax(chatbot.predict(input_sequence2), axis=-1)
+        other_text1 = text2
+        other_text1 = other_text1.lower()
+        other_words1 = other_text1.split()
+        other_num1 = [word_to_num[word] for word in other_words1]
+        given_X1 = other_num1
+        input_sequence1 = pad_sequences([given_X1], maxlen=max_len, padding='post')
+        output_sentence = other_text1+""
+        for _ in range(10):
+            predicted_token = np.argmax(chatbot.predict(input_sequence1), axis=-1)
             predicted_token = predicted_token.item()
             out = num_to_word[predicted_token]
-            # if out == ".":
-                # break
-
+            
+    
             output_sentence += " " + out
-            given_X2 = given_X2[1:]
-            given_X2.append(predicted_token)
-            input_sequence2 = pad_sequences([given_X2], maxlen=max_len, padding='post')
+            if out == ".":
+                break
+            given_X1 = given_X1[1:]
+            given_X1.append(predicted_token)
+            input_sequence1 = pad_sequences([given_X1], maxlen=max_len, padding='post')
+
+        out2 = output_sentence
+
+
+
+
 
-        out2 = output_sentence    
-    
-    st.write("Predicted Text: ")
-    st.write(out2)
-        
-    
-elif option=="26M_OLD":
-    option2 = st.selectbox('Type',('word','sentence'))
-    if option2 == 'word':
-        len2 = 1
-    else:
-        len2 = 13
-    
-else:
-    out2 = "Error: Wrong Model Selected"
     
-    st.write(out2)
+st.write("Predicted Text: ")
+st.write(out2)