app.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
import gradio as gr


def get_sequence(prompt):
    sequences = pipeline(prompt,
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)    

model = "tiiuae/falcon-7b"

tokenizer = AutoTokenizer.from_pretrained(model)

pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)


demo = gr.Interface(inputs='text', outputs='text', fn = get_sequence)
demo.launch()