#!/usr/bin/env python
# encoding: utf-8
import spaces
import gradio as gr
from PIL import Image
import traceback
import re
import torch
import argparse
import numpy as np
from transformers import AutoModel, AutoTokenizer

# README, How to run demo on different devices

# For Nvidia GPUs.
# python web_demo_2.5.py --device cuda

# For Mac with MPS (Apple silicon or AMD GPUs).
# PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo_2.5.py --device mps

# Argparser
# test.py
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer
import bitsandbytes as bnb
import accelerate

model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
model.eval()

image = Image.open('xx.jpg').convert('RGB')
question = 'What is in the image?'
msgs = [{'role': 'user', 'content': question}]

res = model.chat(
    image=image,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True, # if sampling=False, beam_search will be used by default
    temperature=0.7,
    # system_prompt='' # pass system_prompt if needed
)
print(res)

## if you want to use streaming, please make sure sampling=True and stream=True
## the model.chat will return a generator
res = model.chat(
    image=image,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    temperature=0.7,
    stream=True
)

generated_text = ""
for new_text in res:
    generated_text += new_text
    print(new_text, flush=True, end='')