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

MODEL_ID = "mimo-ai/Mimo-V2-Flash"  # exact repo name HF par

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

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    output = model.generate(
        **inputs,
        max_new_tokens=300,
        do_sample=True,
        temperature=0.7
    )
    return tokenizer.decode(output[0], skip_special_tokens=True)

ui = gr.Interface(
    fn=chat,
    inputs=gr.Textbox(lines=5, placeholder="Type your message..."),
    outputs="text",
    title="MIMO V2 Flash – Free HuggingFace Space",
    description="Open-source MIMO V2 Flash running on Hugging Face Spaces"
)

ui.launch()