import gradio as gr def greet(name): return str(int(name)+10) iface = gr.Interface(fn=greet, inputs="text", outputs="text") iface.launch() # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-13b-chat-hf") model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-13b-chat-hf") print('')