app.py

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

model_name = "tiiuae/falcon-rw-1b"  # Use falcon-7b-instruct for GPU

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)

device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

def chat_with_falcon(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        do_sample=True,
        temperature=0.7
    )
    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return reply

gr.Interface(fn=chat_with_falcon, inputs="text", outputs="text", title="Falcon Chatbot").launch()