update app

app.py

@@ -2,19 +2,48 @@ import streamlit as st
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-# Load the tokenizer and model (change 'model_name' to your specific model)
-model_name = "gpt2"  # Replace with your model
+# Define the model name
+model_name = "Qwen/Qwen2.5-1.5B-Instruct"
+
+# Load the model and tokenizer
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Function to generate a response
 def generate_response(prompt):
     if not prompt:
         return "Please enter a prompt."
+
+    # Create the messages for chat-based model
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": prompt}
+    ]
+    
+    # Format the input for the model
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+    # Generate model response
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=512
+    )
+    
+    # Decode and return the response
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
     
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    output = model.generate(**inputs, max_new_tokens=512)
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
     
     return response