Update app.py

app.py

@@ -1,10 +1,10 @@
 import gradio as gr
-from transformers import GPT2LMHeadModel, GPT2Tokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Load pre-trained GPT-2 model and tokenizer
+# Load pre-trained model and tokenizer
 model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
-tokenizer = GPT2Tokenizer.from_pretrained(model_name)
-model = GPT2LMHeadModel.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)  # Use AutoTokenizer to automatically detect the correct tokenizer
+model = AutoModelForCausalLM.from_pretrained(model_name)  # Use AutoModelForCausalLM for causal language models
 
 def generate_response(message, history):
     # Combine the conversation history with the new message
@@ -13,7 +13,7 @@ def generate_response(message, history):
     # Tokenize input text
     inputs = tokenizer.encode(input_text, return_tensors="pt")
     
-    # Generate response using GPT-2
+    # Generate response using the model
     outputs = model.generate(inputs, max_length=50, num_return_sequences=1)
     
     # Decode generated text
@@ -24,8 +24,8 @@ def generate_response(message, history):
 # Create ChatInterface
 demo = gr.ChatInterface(
     fn=generate_response,
-    title="Chat with GPT-2",
-    description="A simple chatbot powered by GPT-2."
+    title="Chat with DeepSeek",
+    description="A simple chatbot powered by DeepSeek."
 )
 
 # Launch the app