Spaces:
Paused
Paused
File size: 4,551 Bytes
5ba996d 009513e 5ba996d 130d634 5ba996d 130d634 896bfe3 130d634 896bfe3 130d634 5d17a8c 130d634 5d17a8c 130d634 9e17522 f1215a7 9e17522 130d634 11deb71 6d8ed0e 896bfe3 130d634 5d17a8c 130d634 5d17a8c 9e17522 0b15668 130d634 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
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
from keras import layers
import numpy as np
import logging
logging.getLogger('tensorflow').setLevel(logging.ERROR)
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',('13M_OLD','26M_OLD')) #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
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:
text = f.read()
text = text.lower()
words = text.split()
loaded_dict = np.load(dict, allow_pickle=True)
word_to_num = loaded_dict["word_to_num"].item()
num_to_word = loaded_dict["num_to_word"].item()
X = []
Y = []
for i in range(len(words)-1):
word = words[i]
next_word = words[i+1]
X.append(word_to_num[word])
Y.append(word_to_num[next_word])
Y.append(0)
X.append(word_to_num[words[-1]])
X_train = pad_sequences([X])
y_train = pad_sequences([Y])
chatbot = TransformerChatbot(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate)
chatbot.load_weights(weights)
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)
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')
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)
|