Update app.py

app.py

@@ -4,6 +4,7 @@ from transformers import AutoModelForSeq2SeqLM
 from transformers import AutoTokenizer
 from transformers import GenerationConfig
 import re
+
 model_name='google/flan-t5-base'
 model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
@@ -21,9 +22,11 @@ Sentiment analysis:
 Sentiments: Negative
 PPrint Key words: tired, long process
 """
+
 def make_prompt(sentence):
     prompt = Examples_to_teach_model+ "Text: " + sentence + "Sentiment analysis:"
     return prompt
+
 def split_conj(text):
     return re.sub('(but|yet|although|however|nevertheless|on the other hand|still|though)', "|", text).split('|')
 
@@ -48,13 +51,19 @@ def get_sentiment_from_llm(review_text):
           skip_special_tokens=True)
         ls_outputs.append("\n".join(output.split('PPrint ')))
     return "\n".join(ls_outputs)
+    
 demo = gr.Blocks()
 sentiment_extr = gr.Interface(
     fn=get_sentiment_from_llm,
     inputs=gr.Textbox(label="Text input", type="text"),
     outputs=gr.Textbox(label="Sentiments", type="text"),
-    title="Sentiments analysis",
-    description="Sentiment analysis and keywords extraction. Powered by prompt tuned flan-t5 from Google. <br> The model is run on small CPU. Please allow 2-3 minutes for longer inputs.",
+    title="Sentiment analysis and keywords extraction",
+    description=""""
+    Enter one or two sentence into the Text Input and click enter to see the sentiments extracted. <br>
+    For longer input, please allow 2-3 minutes as the model is running on small CPU. <br>
+    Base model: Flan-t5 from Google. <br>
+    Prompt tuned by Thuyen Truong for sentiment extraction.
+    """
 )
 with demo:
     gr.TabbedInterface([sentiment_extr], ["Sentiment text analysis"])