Update app.py

app.py

@@ -3,9 +3,12 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
+# Load the model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2-medium", clean_up_tokenization_spaces=True)
+
 model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2-medium")
 
+# Define the initial prompt for the system
 system_prompt = """
 You are an AI model designed to provide concise information about big data analytics across various fields without mentioning the question. Respond with a focused, one-line answer that captures the essence of the key risk, benefit, or trend associated with the topic.
 input: What do you consider the most significant risk of over-reliance on big data analytics in stock market risk management?
@@ -22,12 +25,18 @@ output: Potential widening of the achievement gap if data is not used equitably.
 
 def generate(text):
     try:
+        # Combine the system prompt with the user's input
         prompt = system_prompt + f"\ninput: {text}\noutput:"
-        encoding = tokenizer(prompt, return_tensors="pt", return_attention_mask=True, truncation=True)
-        input_ids = encoding["input_ids"].unsqueeze(0)
-        attention_mask = encoding["attention_mask"].unsqueeze(0)
-        outputs = model.generate(input_ids, attention_mask=attention_mask, max_length=256)
+
+        # Tokenize the input
+        inputs = tokenizer(prompt, return_tensors="pt")
+
+        # Generate the response
+        outputs = model.generate(inputs["input_ids"], max_length=256)
+
+        # Convert the output to text
         response_text = tokenizer.decode(outputs[0], skip_special_tokens=True).split("output:")[-1].strip()
+
         return response_text if response_text else "No valid response generated."
     
     except Exception as e: