prompt = [
    {
        "speaker": "ユーザー",
        "text": "<Img><ImageHere></Img> What can you see?"
    },
    {
        "speaker": "システム",
        "text": "a cat on a table with a laptop"
    },
    {
        "speaker": "ユーザー",
        "text": "猫はどんな体勢をしていますか？"
    },
]
prompt = [
    f"{uttr['speaker']}: {uttr['text']}"
    for uttr in prompt
]
prompt = "\n".join(prompt)
prompt = (
    prompt
    + "\n"
    + "システム: "
)
print(prompt)
"""
ユーザー: <Img><ImageHere></Img> What can you see?
システム: a cat on a table with a laptop
ユーザー: 猫はどんな体勢をしていますか？
システム: 
"""

git clone https://github.com/Vision-CAIR/MiniGPT-4.git
cd ./MiniGPT-4
git checkout 22d8888 # latest version as of July 31, 2023.
wget https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4/resolve/main/customized_mini_gpt4.py
wget https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4/resolve/main/checkpoint.pth

import torch
import requests
from PIL import Image
from minigpt4.processors.blip_processors import Blip2ImageEvalProcessor
from customized_mini_gpt4 import CustomizedMiniGPT4

ckpt_path = "./checkpoint.pth"

model = CustomizedMiniGPT4(gpt_neox_model="rinna/bilingual-gpt-neox-4b")
tokenizer = model.gpt_neox_tokenizer

if torch.cuda.is_available():
    model = model.to("cuda")

if ckpt_path is not None:
    print("Load BLIP2-LLM Checkpoint: {}".format(ckpt_path))
    ckpt = torch.load(ckpt_path, map_location="cpu")
    model.load_state_dict(ckpt['model'], strict=False)

vis_processor = Blip2ImageEvalProcessor()

image_url = "https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4/resolve/main/sample.jpg"
raw_image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
image = vis_processor(raw_image).unsqueeze(0).to(model.device)
image_emb = model.encode_img(image)

embs = model.get_context_emb(prompt, [image_emb])

output_ids = model.gpt_neox_model.generate(
    inputs_embeds=embs,
    max_new_tokens=512,
    do_sample=True,
    temperature=1.0,
    top_p=0.85,
    pad_token_id=tokenizer.pad_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id
)

output = tokenizer.decode(output_ids.tolist()[0], skip_special_tokens=True)
print(output)
"""横になっています。"""

@misc{rinna-bilingual-gpt-neox-4b-minigpt4,
    title = {rinna/bilingual-gpt-neox-4b-minigpt4},
    author = {Mitsuda, Koh and Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4}
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}