Update app.py

app.py

@@ -2,13 +2,15 @@ import transformers
 import streamlit as st
 
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import json
+
+with open('testbook.json') as f:
+    test_book = json.load(f)
 
 tokenizer = AutoTokenizer.from_pretrained("UNIST-Eunchan/bart-dnc-booksum")
 
-tokenizer = AutoTokenizer.from_pretrained("gpt2-large")
 @st.cache
 def load_model(model_name):
-
     model = AutoModelForSeq2SeqLM.from_pretrained("UNIST-Eunchan/bart-dnc-booksum")
     return model
 
@@ -29,14 +31,18 @@ def infer(input_ids, max_length, temperature, top_k, top_p):
     )
     
     return output_sequences
-default_value = "See how a modern neural network auto-completes your text 🤗 This site, built by the Hugging Face team, lets you write a whole document directly from your browser, and you can trigger the Transformer anywhere using the Tab key. Its like having a smart machine that completes your thoughts 😀 Get started by typing a custom snippet, check out the repository, or try one of the examples. Have fun!"
+
+default_value = test_book[0]['book']
+
+'''
+'''
 
 #prompts
-st.title("Write with Transformers 🦄")
+st.title("Book Summarization 📚")
 st.write("The almighty king of text generation, GPT-2 comes in four available sizes, only three of which have been publicly made available. Feared for its fake news generation capabilities, it currently stands as the most syntactically coherent model. A direct successor to the original GPT, it reinforces the already established pre-training/fine-tuning killer duo. From the paper: Language Models are Unsupervised Multitask Learners by Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei and Ilya Sutskever.")
 
 sent = st.text_area("Text", default_value, height = 550)
-max_length = st.sidebar.slider("Max Length", min_value = 10, max_value=256)
+max_length = st.sidebar.slider("Max Length", value = 512,min_value = 10, max_value=1024)
 temperature = st.sidebar.slider("Temperature", value = 1.0, min_value = 0.0, max_value=1.0, step=0.05)
 top_k = st.sidebar.slider("Top-k", min_value = 0, max_value=5, value = 0)
 top_p = st.sidebar.slider("Top-p", min_value = 0.0, max_value=1.0, step = 0.05, value = 0.92)