Update app.py

app.py

@@ -1,3 +1,28 @@
 import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-gr.load("models/meta-llama/Llama-3.3-70B-Instruct").launch()
+# Load the model and tokenizer
+model_name = "models/meta-llama/Llama-3.3-70B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def chat_with_model(user_input):
+    # Encode the user input and generate a response
+    inputs = tokenizer.encode(user_input, return_tensors="pt")
+    output = model.generate(inputs, max_length=150, num_return_sequences=1)
+    
+    # Decode the generated response
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# Create a Gradio interface for chatting
+iface = gr.Interface(
+    fn=chat_with_model,
+    inputs=gr.Textbox(label="You:"),
+    outputs=gr.Textbox(label="Bot:"),
+    title="Llama Chatbot",
+    description="Chat with Llama-3.3-70B-Instruct model."
+)
+
+# Launch the app
+iface.launch()