from transformers import pipeline import gradio as gr pipe1 = pipeline(model = "meta-llama/Llama-3.2-1B-Instruct") #pipe2 = pipeline(model = "meta-llama/Llama-3.2-3B-Instruct") def inference(input): output = pipe1( text_inputs = input ) return output[0]['generated_text'][len(input):] app = gr.Interface( fn = inference, inputs = [gr.Textbox(label = "Input")], outputs = [gr.Textbox(label = "Output")], title = "Demo", examples = [ ["Hello, Llama."] ] ).launch()