You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Model Details

Model Description

This repository provides Asagi-14B, a large-scale Japanese Vision & Language Model (VLM). Asagi-14B has been trained on an extensive Japanese dataset, incorporating a diverse range of data sources.

A significant portion of the training data is synthesized using models such as the Japanese large language model (CALM3-22B-Chat) and the English Vision & Language Model (Phi3.5-vision-instruct).

Importantly, we do not use LLMs that restrict the usage of their outputs in the license terms (e.g., GPT-4) to synthesize the training data.

Model components Model / Architecture Parameters
Vision encoder siglip-so400m-patch14-384 428M
Projector 2-layer MLP 64M
LLM llm-jp-3-13b-instruct 13B

Usage

Requirements

transformers==4.45.1
accelerate==0.34.2
torch==2.4.0
torchvision==0.19.0

How to use

import requests
import torch
import transformers
from PIL import Image
from transformers import AutoModel, AutoProcessor, GenerationConfig

transformers.set_seed(42)
model_path = "MIL-UT/Asagi-14B"
processor = AutoProcessor.from_pretrained(model_path)
model = AutoModel.from_pretrained(
    model_path, trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

generation_config = GenerationConfig(
    do_sample=True,
    num_beams=5,
    max_new_tokens=256,
    temperature=0.7,
    repetition_penalty=1.5
)

prompt = ("以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。\n\n"
            "### 指示:\n<image>\nこの画像を見て、次の質問に詳細かつ具体的に答えてください。この写真はどこで撮影されたものか教えてください。また、画像の内容についても詳しく説明してください。\n\n### 応答:\n")

# sample image
sample_image_url = "https://raw.githubusercontent.com/uehara-mech/uehara-mech.github.io/refs/heads/master/images/shibuya.jpg"
image = Image.open(requests.get(sample_image_url, stream=True).raw)

inputs = processor(
    text=prompt, images=image, return_tensors="pt"
)
inputs_text = processor.tokenizer(prompt, return_tensors="pt")
inputs['input_ids'] = inputs_text['input_ids']
inputs['attention_mask'] = inputs_text['attention_mask']
for k, v in inputs.items():
    if v.dtype == torch.float32:
        inputs[k] = v.to(model.dtype)
inputs = {k: inputs[k].to(model.device) for k in inputs if k != "token_type_ids"}

generate_ids = model.generate(
    **inputs,
    generation_config=generation_config
)
generated_text = processor.batch_decode(
    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]

# do not print the prompt
if "<image>" in prompt:
    prompt = prompt.replace("<image>", " ")
generated_text = generated_text.replace(prompt, "")

print(f"Generated text: {generated_text}")

# >>> Generated text:  この写真は渋谷スクランブル交差点の夜景を撮影したものです。渋谷スクランブル交差点は、東京都渋谷区に位置する有名な交差点で、多くの人々が行き交う場所として知られています。写真には、高層ビル群やネオンサイン、街灯などが写っており、都会の活気とエネルギーを感じることができます。

Example

Prompt Output
この画像を見て、次の質問に詳細かつ具体的に答えてください。この写真はどこで撮影されたものか教えてください。また、画像の内容についても詳しく説明してください。 この写真は渋谷スクランブル交差点の夜景を撮影したものです。渋谷スクランブル交差点は、東京都渋谷区に位置する有名な交差点で、多くの人々が行き交う場所として知られています。写真には、高層ビル群やネオンサイン、街灯などが写っており、都会の活気とエネルギーを感じることができます。

More Examples

Click to expand
Prompt Output
この画像を見て、次の指示に詳細かつ具体的に答えてください。この写真の内容について詳しく教えてください。 この写真は、東京のレインボーブリッジを背景にした都市景観を撮影したものです。橋は白と灰色の塗装が施されており、水の上に優雅にアーチを描いています。空は澄み切った青色で、少数の雲が浮かんでいます。遠くには高層ビルが立ち並ぶ都市の風景が見えます。
Prompt Output
この画像を見て、次の質問に詳細かつ具体的に答えてください。この写真について評価してください。 この写真は非常に美しいです。東京タワーの赤と白のコントラストが鮮やかで、青空と白い雲との対比が印象的です。周囲の緑豊かな木々と街灯が都会的な雰囲気を醸し出しており、全体的にバランスの取れた構図となっています。
Prompt Output
この画像を見て、次の質問に詳細かつ具体的に答えてください。この写真の神社について、細かいところまで詳しく説明してください。 この写真に写っている神社は、日本の伝統的な建築様式を反映しています。白い壁とオレンジ色の柱が特徴的で、屋根は緑色の瓦で覆われています。神社の入り口には朱色の鳥居が立っており、これは神聖な場所への入り口を示す象徴的な門です。鳥居の両脇にはしめ縄が飾られており、神聖な雰囲気を醸し出しています。また、神社の前には石畳が敷かれており、これは参拝者が神聖な場所に足を踏み入れる際の敬意を表すためのものです。この神社は、現代の都市部にありながらも、日本の伝統的な文化や信仰を現代に伝える重要な役割を果たしています。
Prompt Output
この画像を見て、次の指示に詳細かつ具体的に答えてください。これは日本庭園の中でも、どのような形式に分類される庭園ですか?また、その理由は何ですか? これは日本庭園の中でも、池泉回遊式庭園と呼ばれる形式の庭園です。池泉回遊式庭園は、池を中心に配置し、その周りを回遊できるように設計された庭園です。この形式の庭園は、自然の美しさを最大限に引き出し、訪れる人々に静寂と安らぎを提供することを目的としています。
Prompt Output
この画像を見て、次の質問に詳細に答えてください。この画像の場所を舞台とした小説のあらすじを書いてください。 この画像の場所を舞台とした小説のタイトルは「階段の秘密」です。物語は、都会の喧騒から離れた静かな路地裏にある古い石造りの階段を舞台に展開します。主人公は、この階段を登りながら、過去と現在が交錯する不思議な体験をしていきます。階段の途中には、歴史を感じさせる苔むした石壁や、伝統的な木造建築の建物が立ち並んでいます。主人公は、階段を登るたびに、過去の出来事や人々の記憶に触れ、自分自身の過去と向き合います。そして、階段の頂上にたどり着くと、そこに隠された秘密が明かされるのです。

Training Details

Training Data

Dataset Preprocess Stage1 Stage2 Size
ROIS (Ours) Synthesized 8.4M
Japanese image text pairs Synthesized 4.4M
Wikipedia Synthesized 2.5M
Open Images Translated 680K
DCI Translated 7K
CommonCatalog CC-BY Translated 3.5M
LLaVA-Pretrain-JA 550K
STAIR Captions 410K
Flickr-JP 160K
YJ Captions 130K
Japanese Pascal 5K
ArtBench Synthesized 100K
GQA Translated 1.9M
VQA v2 Translated 880K
A-OKVQA Translated 34K
OK-VQA Translated 18K
Japanese Visual Genome Translated 1.6M
PangeaInstruct 93K

Note: ROIS (Ours) is a newly collected dataset crawled from the web specifically for this project. The dataset consists of image and raw text pairs, which are used to synthesize the training data.

Evaluation

We evaluated our model using Heron-Bench, JA-VLM-Bench-in-the-Wild, and JA-VG-VQA-500. We used eval-mm library for this evaluation.

Here, models with "†" are not trained with GPT-generated data. Bold numbers indicate the best performance among all models, and underlined numbers indicate the best performance among models not trained with GPT-generated data.

Model LM Size Heron-Bench (LLM (%)) JA-VLM-Bench-In-the-Wild (ROUGE-L) JA-VLM-Bench-In-the-Wild (LLM (/5.0)) JA-VG-VQA-500 (ROUGE-L) JA-VG-VQA-500 (LLM (/5.0))
Japanese InstructBLIP Alpha† 7B 14.0 20.8 2.42 - -
Japanese Stable VLM† 7B 24.2 23.3 2.47 - -
LLaVA-CALM2-SigLIP† 7B 43.3 47.2 3.15 17.4 3.21
Llama-3-EvoVLM-JP-v2 8B 39.3 41.4 2.92 23.5 2.96
VILA-jp 13B 57.2 52.3 3.69 16.2 3.62
Asagi-2B† 1.8B 44.7 48.8 3.26 53.7 3.69
Asagi-4B† 3.7B 49.3 49.6 3.38 55.6 3.78
Asagi-8B† 7.2B 54.7 49.4 3.45 56.43 3.84
Asagi-14B† 13B 55.8 50.8 3.44 56.8 3.84
GPT-4o - 87.6 37.6 3.85 12.1 3.58

Risks and Limitations

The models released here are in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.

Model Card Authors

Kohei Uehara

Downloads last month
15
Safetensors
Model size
14.2B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for MIL-UT/Asagi-14B

Finetuned
(11)
this model

Collection including MIL-UT/Asagi-14B