app.py

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

# Load the model and tokenizer
model_name = r"bigscience/bloomz-1b1"
#"bigscience/bloomz-560m"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=300,
            temperature=0.9,
            do_sample=True,
            top_k=50,
            top_p=0.95
        )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Gradio interface
demo = gr.Interface(fn=generate_text,
                    inputs=gr.Textbox(lines=2, placeholder="Enter a prompt..."),
                    outputs="text",
                    title="🌍 BLOOMZ-560M Multilingual Generator")

demo.launch()