MoAI-7B / README.md
BK-Lee's picture
Update README.md
1375af5 verified
|
raw
history blame
2 kB
metadata
license: mit

Simple running code is based on MoAI-Github.

You need only the following seven steps.

[0] Download Github Code of MoAI, install the required libraries, set the necessary environment variable (README.md explains in detail! Don't Worry!).

git clone https://github.com/ByungKwanLee/MoAI
bash install

[1] Loading Image

from PIL import Image
from torchvision.transforms import Resize
from torchvision.transforms.functional import pil_to_tensor
image_path = "figures/moai_mystery.png"
image = Resize(size=(490, 490), antialias=False)(pil_to_tensor(Image.open(image_path)))

[2] Instruction Prompt

prompt = "Describe this image in detail."

[3] Loading MoAI

from moai.load_moai import prepare_moai
moai_model, moai_processor, seg_model, seg_processor, od_model, od_processor, sgg_model, ocr_model \
    = prepare_moai(moai_path='BK-Lee/MoAI-7B', bits=4, grad_ckpt=False, lora=False, dtype='fp16')

[4] Pre-processing for MoAI

moai_inputs = moai_model.demo_process(image=image, 
                                    prompt=prompt, 
                                    processor=moai_processor,
                                    seg_model=seg_model,
                                    seg_processor=seg_processor,
                                    od_model=od_model,
                                    od_processor=od_processor,
                                    sgg_model=sgg_model,
                                    ocr_model=ocr_model,
                                    device='cuda:0')

[5] Generate

import torch
with torch.inference_mode():
    generate_ids = moai_model.generate(**moai_inputs, do_sample=True, temperature=0.9, top_p=0.95, max_new_tokens=256, use_cache=True)

[6] Decoding

answer = moai_processor.batch_decode(generate_ids, skip_special_tokens=True)[0].split('[U')[0]
print(answer)