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

model_id = "NousResearch/zephyr-1.3b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float32
)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def generate_text(prompt):
    output = pipe(prompt, max_new_tokens=200, do_sample=True, temperature=0.7)
    return output[0]["generated_text"]

demo = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(lines=4, placeholder="Escribe algo..."),
    outputs="text",
    title="Generador de texto - Zephyr 1.3B (CPU compatible)"
)

demo.launch()