Create app.py

app.py

@@ -0,0 +1,31 @@
+import streamlit as st
+import tensorflow as tf
+from transformers import TFGPT2LMHeadModel, GPT2Tokenizer
+import pandas as pd
+import numpy as np
+
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+model = TFGPT2LMHeadModel.from_pretrained("gpt2", pad_token_id=tokenizer.eos_token_id)
+
+def func(sentence, max_length, temperature):
+    input_ids = tokenizer.encode(sentence, return_tensors='tf')
+    output_list = model.generate(
+        input_ids, 
+        do_sample=True, 
+        max_length=max_length,
+        temperature=temperature,
+        top_p=0.92, 
+        top_k=0,
+        num_return_sequences=5
+    )
+    output_strs = [tokenizer.decode(output, skip_special_tokens=True) for output in output_list]
+    return output_strs
+
+sentence = st.text_input(label="Sentence to complete")
+max_length = st.slider(label="Max Length", min_value=5, max_value=25, value=10, step=1)
+temperature = st.slider(label="Temperature", min_value=0.1, max_value=10, value=0.1)
+
+if st.button('Click to generate possible completions'):
+    outputs_strs = func(sentence, max_length, temperature)
+    for output in outputs_strs:
+        st.write(output)