Update app.py

app.py

@@ -1,42 +1,7 @@
-import streamlit as st
-from datasets import load_dataset
-from transformers import AutoModelForSeq2SeqLM
-from transformers import AutoTokenizer
-from transformers import GenerationConfig
+import streamlit as st from transformers import pipeline 
+classifier = pipeline("sentiment-analysis") 
+text = st.text_enter("Enter your text") 
 
-huggingface_dataset_name = "knkarthick/dialogsum"
-dataset = load_dataset(huggingface_dataset_name)
-
-model_name = 'google/flan-t5-base'
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
-
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
-
-# select an example
-example_index = [40]
-
-# get the dialogue
-dialogue = dataset['test'][example_index]['dialogue']
-
-# get the human summary
-summary = dataset['test'][example_index]['summary']
-
-# Configurations
-# generation_config = GenerationConfig(max_new_tokens=50, do_sample=True, temperature=0.7)
-generation_config = GenerationConfig(max_new_tokens=50)
-
-# Encode input:
-inputs_encoded = tokenizer(dialogue, return_tensors='pt')
-
-# Model Output:
-model_output = model.generate(inputs_encoded["input_ids"], generation_config=generation_config)[0]
-
-# Decode the output
-zero_output = tokenizer.decode(model_output, skip_special_tokens=True)
-
-
-print("Input: ", dialogue)
-print(dash_line)
-print( "Human summary: ", summary)
-print(dash_line)
-print("Model Output: ", zero_output)
+if text : 
+    out = classifier(text) 
+    st.json(out)