Create app.py

app.py

@@ -0,0 +1,105 @@
+import streamlit as st
+import tensorflow as tf
+from keras.layers import Input, Dense, Embedding, MultiHeadAttention
+from keras.layers import Dropout, LayerNormalization
+from keras.models import Model
+from keras.utils import pad_sequences
+import numpy as np
+
+class TransformerChatbot(Model):
+    def __init__(self, vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate):
+        super(TransformerChatbot, self).__init__()
+        self.embedding = Embedding(vocab_size, d_model)
+        self.attention = MultiHeadAttention(num_heads=n_head, key_dim=d_model)
+        self.norm1 = LayerNormalization(epsilon=1e-6)
+        self.dropout1 = Dropout(dropout_rate)
+        self.dense1 = Dense(ff_dim, activation="relu")
+        self.dense2 = Dense(d_model)
+        self.norm2 = LayerNormalization(epsilon=1e-6)
+        self.dropout2 = Dropout(dropout_rate)
+        self.flatten = tf.keras.layers.Flatten()
+        self.fc = Dense(vocab_size, activation="softmax")
+        self.max_len = max_len
+
+    def call(self, inputs):
+        x = self.embedding(inputs)
+        # Masking
+        mask = self.create_padding_mask(inputs)
+        attn_output = self.attention(x, x, x, attention_mask=mask)
+        x = x + attn_output
+        x = self.norm1(x)
+        x = self.dropout1(x)
+        x = self.dense1(x)
+        x = self.dense2(x)
+        x = self.norm2(x)
+        x = self.dropout2(x)
+        x = self.fc(x)
+        return x
+
+    def create_padding_mask(self, seq):
+        mask = tf.cast(tf.math.equal(seq, 0), tf.float32)
+        return mask[:, tf.newaxis, tf.newaxis, :]
+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',('12M Param')) #option is stored in this variable
+#Textbox for text user is entering
+st.subheader("Enter the text you'd like to analyze.")
+text = st.text_input('Enter word: ') #text is stored in this variable
+
+if option == '12M Param':
+    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 = loaded_dict["X"].item()
+    Y = loaded_dict["Y"].item()
+    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("predict3")
+    chatbot.build(input_shape=(None, max_len)) # Build the model
+    chatbot.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
+    other_text1 = text
+    for i in range(1):
+
+        other_text1 = other_text1.lower()
+        other_words1 = other_text1.split()
+        if len(other_words1) > 1:
+            st.write("Error: Found more than 1 word . There should not be more than one word in the prompt ")
+        for word in other_words1:
+            if word not in word_to_num:
+                st.write("Error: The word ` ",word," ` doesn't exist in the vocabulary and hence the model wasn't train on that. ")
+            else:
+                other_num1 = word_to_num[word]
+
+        given_X1 = other_num1
+        input_sequence1 = pad_sequences([given_X1], maxlen=max_len, padding='post')
+        output_sentence = other_text1 + ""
+        for _ in range(16):
+            predicted_token = np.argmax(chatbot.predict(input_sequence1), axis=-1)
+            predicted_token = predicted_token.item()
+            out = num_to_word[predicted_token]
+            
+
+            output_sentence += " " + out
+            if out == ".":
+                break
+            given_X1 = given_X1[1:]
+            given_X1.append(predicted_token)
+            input_sequence1 = pad_sequences([given_X1], maxlen=max_len, padding='post')
+        out = output_sentence
+        
+    
+else:
+    out = "Wrong Model"
+    
+st.write("Predicted Text: ")
+st.write(out)