app.py

# -*- coding: utf-8 -*-
"""falcon-7b-instruct.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1VY6GckUeF6uVKiDGymZZgtxiO7plJvo4

https://huggingface.co/tiiuae/falcon-7b-instruct"""

"""## Import libraries"""

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

"""## Define the model"""

model = "tiiuae/falcon-7b-instruct"

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",
)

"""## Generate Text Function"""

def generate_text(text):
  sequences = pipeline(
      text,
      max_length=200,
      do_sample=True,
      top_k=10,
      num_return_sequences=1,
      eos_token_id=tokenizer.eos_token_id,
  )
  for seq in sequences:
      return(f"Result: {seq['generated_text']}")

#Create a Gradio interface
iface = gr.Interface(
	fn=generate_text,
	inputs="text",
	outputs="text",
	title="ChatBot",
	description="Type anything you want to chat"
)