app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
#model_name = "tiiuae/falcon-11b"
model_name = "tiiuae/falcon-7b"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the inference function
def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(inputs['input_ids'], max_length=50)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create the Gradio interface
interface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
interface.launch()