Update app.py

app.py

@@ -1,22 +1,38 @@
-# import streamlit as st
-# from transformers import pipeline
-# generator= pipeline("text_generation", model="gpt2-large")
-# def generate_blog(topic):
-#   res= generator(max_length=400, num_return_sequences=3)
-#   return res[0]["generate_text"]
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+import streamlit as st
 
+# Initialize the tokenizer and model
+model_name = 'gpt2-large'
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
 
+text= st.text_area("Enter your Topic: ")
 
-# text = st.text_area("Enter a topic")
-# if text:
-#     out=generate_blog(text)
-#     st.json(out)
-
-import streamlit as st
-from transformers import pipeline
-pipe = pipeline("sentiment-analysis")
-text= st.text_area("Enter your text")
 
 if text:
-    output = pipe(text)
-    st.json(output)
+    # Encode input text
+    encoded_input = tokenizer(text, return_tensors='pt')
+
+    # Generate text
+    output = model.generate(
+        input_ids=encoded_input['input_ids'],
+        max_length=50,
+        num_return_sequences=1,
+        no_repeat_ngram_size=2,
+        top_p=0.95,
+        top_k=50
+    )
+
+    # Decode generated text
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    st.json(generated_text)
+
+# import streamlit as st
+# from transformers import pipeline
+# pipe = pipeline("sentiment-analysis")
+# text= st.text_area("Enter your text")
+
+# if text:
+#     output = pipe(text)
+#     st.json(output)