Update app.py

app.py

@@ -1,13 +1,33 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("gpt2")
-model = AutoModelForCausalLM.from_pretrained("gpt2")
+# Load the tokenizer and model
+model_name = "meta-llama/Llama-3.2-1B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-def generate(text):
-    inputs = tokenizer.encode(text, return_tensors='pt')
-    outputs = model.generate(inputs, max_length=100, do_sample=True)
-    generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return generated
+# Define the generation function
+def generate_response(prompt):
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    outputs = model.generate(
+        inputs,
+        max_length=512,
+        num_return_sequences=1,
+        do_sample=True,
+        temperature=0.7,
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-gr.Interface(fn=generate, inputs="text", outputs="text").launch()
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(lines=5, placeholder="Enter your prompt here..."),
+    outputs=gr.Textbox(label="Generated Response"),
+    title="Llama-3.2-1B-Instruct Model",
+    description="A simple interface to interact with the Llama-3.2-1B-Instruct model.",
+)
+
+# Launch the app
+if __name__ == "__main__":
+    interface.launch()