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

model_id = "hf-100/mistral-spellbound-research"

tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    use_auth_token=True
)

def generate(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    output = model.generate(
        **inputs,
        max_new_tokens=300,
        temperature=0.8,
        top_p=0.95,
        do_sample=True
    )
    return tokenizer.decode(output[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=generate,
    inputs=gr.Textbox(lines=4, placeholder="Enter your prompt..."),
    outputs="text",
    title="Spellbound Model - Roleplay AI",
    description="Powered by hf-100/mistral-spellbound-research"
)

iface.launch()