🚀 DolphinVision 72b 🐬
DolphinVision 72bは、Quan Nguyen (qnguyen3/stablequan)、Eric Hartford、およびCognitive Computationsによって選定され、訓練されたマルチモーダルモデルです。このモデルは、画像に関する推論やコメントを行う能力を持ち、他の人気モデルが拒否するような画像に対しても対応できます。
Discord: https://discord.gg/h3K4XGj2RH
🤝 スポンサーに感謝
🚀 クイックスタート
DolphinVisionはマルチモーダルモデルで、画像に関する推論やコメントを行うことができます。以下は、このモデルを使用するためのコード例です。
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import warnings
transformers.logging.set_verbosity_error()
transformers.logging.disable_progress_bar()
warnings.filterwarnings('ignore')
torch.set_default_device('cuda')
model_name = 'cognitivecomputations/dolphin-vision-72b'
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map='auto',
trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
model_name,
trust_remote_code=True)
prompt = 'Describe this image in detail'
messages = [
{"role": "user", "content": f'<image>\n{prompt}'}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
print(text)
text_chunks = [tokenizer(chunk).input_ids for chunk in text.split('<image>')]
input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1], dtype=torch.long).unsqueeze(0)
image = Image.open('/path/to/image.png')
image_tensor = model.process_images([image], model.config).to(dtype=model.dtype)
output_ids = model.generate(
input_ids,
images=image_tensor,
max_new_tokens=2048,
use_cache=True)[0]
print(tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip())
💻 使用例
基本的な使用法

<|im_start|>user
: do OCR on all the text
<|im_start|>assistant
: 画像内のテキストは以下の通りです。
- STOP USING DOCKER
- Applications were not meant to be trapped in virtual jars like digital fireflies
- Years of software development, yet no one questioned why we were putting programs in imaginary boats
- Let's containerize our monolith. I'll just quickly spin up 17 microservices. Statements dreamt up by the utterly deranged
- Observe the whale-sized deception they fooled us with all this time
- These are real images used to explain Docker
- "Yay Matey, I'd like to run my website in a virtual sea"
- They have played us for absolute fools
このテキストは、ソフトウェア開発におけるDockerの使用に対する風刺的なコメントで、ユーモアと誇張を使ってその慣行に疑問を投げかけています。
📊 ベンチマーク
モデル |
VQA v2 |
MMBench |
MMMU (Eval) |
MathVista |
RealWorldQA |
Dolphin-Vision-72B |
83.6 |
81.2 |
45.7 |
47.25 |
66.4 |
GPT-4V |
84.4 |
78.1 |
52.4 |
- |
67.9 |
📄 ライセンス
- ライセンス: other
- ライセンス名: tongyi-qianwen
- ベースモデル: Qwen/Qwen2-72B
タグ
- generated_from_trainer
- axolotl
データセット
- cognitivecomputations/Dolphin-2.9
- teknium/OpenHermes-2.5
- m-a-p/CodeFeedback-Filtered-Instruction
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- microsoft/orca-math-word-problems-200k
- Locutusque/function-calling-chatml
- internlm/Agent-FLAN