File size: 14,617 Bytes
091f1a3 87dbe75 091f1a3 87dbe75 091f1a3 87dbe75 091f1a3 87dbe75 091f1a3 87dbe75 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 |
---
library_name: transformers
datasets:
- 5CD-AI/Viet-OCR-VQA
- 5CD-AI/Viet-Doc-VQA
- 5CD-AI/Viet-Doc-VQA-II
- Vi-VLM/Vista
- 5CD-AI/Viet-Receipt-VQA
- 5CD-AI/Viet-Sketches-VQA
- 5CD-AI/Viet-Geometry-VQA
- 5CD-AI/Viet-Wiki-Handwriting
- 5CD-AI/Viet-ComputerScience-VQA
- 5CD-AI/Viet-Handwriting-gemini-VQA
- 5CD-AI/Viet-Menu-gemini-VQA
- 5CD-AI/Viet-Vintext-gemini-VQA
- 5CD-AI/Viet-OpenViVQA-gemini-VQA
- 5CD-AI/Viet-Resume-VQA
- 5CD-AI/Viet-ViTextVQA-gemini-VQA
language:
- vi
- en
pipeline_tag: visual-question-answering
---
<div align="center">
<img src="Vintern_logo.png" width="700"/>
</div>
## Vintern-1B-v2 ❄️ (Viet-InternVL2-1B-v2) [\[🤗 HF Demo\]](https://huggingface.co/spaces/khang119966/Vintern) - The LLaVA 🌋 Challenger
We are excited to introduce **Vintern-1B-v2** the Vietnamese 🇻🇳 multimodal model that combines the advanced Vietnamese language model [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct)[1] with the latest visual model, [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)[2], CVPR 2024. This model excels in tasks such as OCR-VQA, Doc-VQA, and Chart-VQA,... With only 1 billion parameters, it is **4096 context length** finetuned from the Viet-InternVL-1B model on over 3 million specialized image-question-answer pairs for optical character recognition 🔍, text recognition 🔤, document extraction 📑, and general QA. The model can be integrated into various on-device applications 📱, demonstrating its versatility and robust capabilities.
## Model Details
| Model Name | Vision Part | Language Part |
| :------------------: | :---------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------: |
| Vintern-1B-v2 | [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px) | [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) |
Vintern-1B-v2 is a multimodal large language model series, featuring models of various sizes. For each size, we release instruction-tuned models optimized for multimodal tasks. Vintern-1B-v2 consists of [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px), an MLP projector, and [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
## Training details 📚
The fine-tuning dataset was meticulously sampled in part from the following datasets:
- [Viet-OCR-VQA](https://huggingface.co/datasets/5CD-AI/Viet-OCR-VQA) 📄
- [Viet-Doc-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Doc-VQA) 📚
- [Viet-Doc-VQA-II](https://huggingface.co/datasets/5CD-AI/Viet-Doc-VQA-II) 📑
- [Vista](https://huggingface.co/datasets/Vi-VLM/Vista) 🌄
- [Viet-Receipt-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Receipt-VQA) 🧾
- [Viet-Sketches-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Sketches-VQA) ✏️
- [Viet-Geometry-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Geometry-VQA) 📐
- [Viet-Wiki-Handwriting](https://huggingface.co/datasets/5CD-AI/Viet-Wiki-Handwriting) 📝
- [Viet-ComputerScience-VQA](https://huggingface.co/datasets/5CD-AI/Viet-ComputerScience-VQA) 💻
- [Viet-Handwriting-gemini-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Handwriting-gemini-VQA) ✍️
- [Viet-Menu-gemini-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Menu-gemini-VQA) 🍽️
- [Viet-Vintext-gemini-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Vintext-gemini-VQA) 🏷️
- [Viet-OpenViVQA-gemini-VQA](https://huggingface.co/datasets/5CD-AI/Viet-OpenViVQA-gemini-VQA) 🔍
- [Viet-Resume-VQA](https://huggingface.co/datasets/5CD-AI/Viet-Resume-VQA) 📃
- [Viet-ViTextVQA-gemini-VQA](https://huggingface.co/datasets/5CD-AI/Viet-ViTextVQA-gemini-VQA) 📑
## Benchmarks 📈
Since there are still many different metrics that need to be tested, we chose a quick and simple metric first to guide the development of our model. Our metric is inspired by Lavy[4]. For the time being, we are using GPT-4 to evaluate the quality of answers on two datasets: OpenViVQA and ViTextVQA. Detailed results can be found at the provided . The inputs are images, questions, labels, and predicted answers. The model will return a score from 0 to 10 for the corresponding answer quality. The results table is shown below.
<table border="1" cellspacing="0" cellpadding="5">
<tr align="center">
<td rowspan="2"><b>Model</b></td>
<td colspan="2"><b>Gpt4o-Score</b></td>
</tr>
<tr align="center">
<td><b>OpenViVQA-dev</b></td>
<td><b>ViTextVQA-dev</b></td>
</tr>
<tr align="center">
<td align="left">Vintern-1B</td>
<td>7.1/10</td>
<td>7.6/10</td>
</tr>
<tr align="center">
<td align="left">Vintern-1B-v2</td>
<td>....</td>
<td>....</td>
</tr>
</table>
We are still working on more detailed benchmarks.
## Examples
<div align="center">
<img src="ex_images/1.jpg" width="500"/>
</div>
```
User: <image>
Mô tả hình ảnh một cách chi tiết.
Assistant: Bức ảnh là một giấy tờ có tiêu đề "SƠ YẾU LÝ LỊCH" được in trên nền màu xanh dương nhạt. Phía trên cùng bên trái là dòng chữ "GIÁO HỘI PHẬT GIÁO VIỆT NAM", bên phải là dòng chữ "CỘNG HÒA XÃ HỘI CHỦ NGHĨA VIỆT NAM". Dưới tiêu đề là thông tin cá nhân của người được sơ yếu lý lịch, bao gồm:
- Họ và tên khai sinh: VƯƠNG TẤN VIỆT
- Họ và tên gia pha: HỒ CHÍ VIỆT
- Chân danh, Pháp hiệu: CHÂN QUANG
- Ngày và nơi sinh: 09/12/1959 tại Buôn Mê Thuột
- Giấy CMND số: 273038848... cấp tại CA Vũng Tàu ngày 04/05/2005.
- Quê quán: Nghệ An
- Hộ khẩu thường trú: Chùa Phật Quang - Chu Hai - Tân Hải - Tân Hải - Tân Thành - BR. VT
- Phòng ở: Chùa Phật Quang - Chu Hai - Tân Hải - Tân Thành - BR. VT
- Trình độ: + Văn hóa: Cử nhân Anh Văn
- + Ngoại ngữ: + Phát học (chuyên môn): Diễn giảng
- Ngày và nơi xuất trình: 15/01/1980 tại Thiên Viện Thường Chiểu
```
<div align="center">
<img src="ex_images/2.jpg" width="500"/>
</div>
```
User: <image>
Mô tả hình ảnh một cách chi tiết.
Assistant: Bức ảnh chụp một hóa đơn của cửa hàng Circle K Việt Nam. Hóa đơn có tiêu đề "CIRCLE K VIETNAM" ở đầu trang, bên dưới là thông tin liên lạc của cửa hàng: "113 Trần Đại Nghĩa - Hà Nội", "Date: Oct 5 2019 06:39 PM SFB",
"Cashier: 5360-Linh Luong Thi Thuy", "Description: 1 DASANI Bottled Water 1.5L+1PT 12.000", "Item(s) (VAT included): 12.000", "CASH", "CHANGE", "Chỉ xuất hóa đơn trong ngày", "Xin cảm ơn quy khách!"
```
<div align="center">
<img src="ex_images/3.jpg" width="400"/>
</div>
```
User: <image>
Mô tả hình ảnh một cách chi tiết.
Assistant: Bức ảnh là một thông báo tuyển dụng công tác viên kinh doanh của FPT Telecom Bình Thuận. Bố cục được chia thành 4 phần chính:
1. **Phần tiêu đề:** Gồm logo FPT Telecom Bình Thuận và dòng chữ "FPT TELECOM BÌNH THUẬN TUYỂN DỤNG CÔNG TÁC VIÊN KINH DOANH".
2. **Phần lịch phỏng vấn:** Liệt kê thời gian và ngày tháng cụ thể cho lịch phỏng vấn (9h00 - 10h00 thứ Sáu hàng tuần).
3. **Phần chi tiết công việc:** Liệt kê các nhiệm vụ liên quan đến công việc, bao gồm:
- Tìm kiếm thông tin, tiếp cận khách hàng tiềm năng.
- Tư vấn, giải thích cho khách hàng về dịch vụ của FPT Telecom.
- Thực hiện thủ tục ký kết hợp đồng với khách hàng.
4. **Phần yêu cầu công việc:** Liệt kê các yêu cầu cần thiết cho ứng viên, bao gồm:
- Nam, nữ không giới hạn độ tuổi.
- Đam mê kinh doanh.
- Không cần kinh nghiệm.
- Phù hợp với Sinh viên, người cần kiếm thêm thu nhập, làm online,....
5. **Phần quyền lợi:** Liệt kê các quyền lợi mà ứng viên sẽ nhận được, bao gồm:
- Thời gian linh động.
- Thu nhập hấp dẫn.
- Môi trường làm việc thân thiện, được hướng dẫn tận tình.
- Cơ hội trở thành nhân viên chính thức của FPT và được hưởng các chế độ, quyền lợi dành cho nhân viên chính thức.
6. **Phần hồ sơ chuẩn bị:** Liệt kê các giấy tờ cần chuẩn bị cho ứng viên, bao gồm:
- 01 Bản sao hộ khẩu có xác thực của địa phương.
- 01 Bản sao CMND có xác thực của địa phương.
7. **Phần thông tin:**
- Địa chỉ VP: 07 Tuyên Quang - Phan Thiết - Bình Thuận.
- Liên hệ: Ms.Lộc - 0908 391 305.
8. **Phần lưu ý:** Nêu rõ FPT Telecom không thu bất kỳ khoản phí nào từ ứng viên.
```
## Quickstart
Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.
[**Quickstart with Google Colab📒 ⬅️ ⬅️**](https://colab.research.google.com/drive/1ZD1oB56PF0lF66RCuTVJYLTEV0tM3CFf?usp=sharing)
```python
import numpy as np
import torch
import torchvision.transforms as T
# from decord import VideoReader, cpu
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer
IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)
def build_transform(input_size):
MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
transform = T.Compose([
T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
T.ToTensor(),
T.Normalize(mean=MEAN, std=STD)
])
return transform
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
best_ratio_diff = float('inf')
best_ratio = (1, 1)
area = width * height
for ratio in target_ratios:
target_aspect_ratio = ratio[0] / ratio[1]
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
if ratio_diff < best_ratio_diff:
best_ratio_diff = ratio_diff
best_ratio = ratio
elif ratio_diff == best_ratio_diff:
if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
best_ratio = ratio
return best_ratio
def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
orig_width, orig_height = image.size
aspect_ratio = orig_width / orig_height
# calculate the existing image aspect ratio
target_ratios = set(
(i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
i * j <= max_num and i * j >= min_num)
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
# find the closest aspect ratio to the target
target_aspect_ratio = find_closest_aspect_ratio(
aspect_ratio, target_ratios, orig_width, orig_height, image_size)
# calculate the target width and height
target_width = image_size * target_aspect_ratio[0]
target_height = image_size * target_aspect_ratio[1]
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
# resize the image
resized_img = image.resize((target_width, target_height))
processed_images = []
for i in range(blocks):
box = (
(i % (target_width // image_size)) * image_size,
(i // (target_width // image_size)) * image_size,
((i % (target_width // image_size)) + 1) * image_size,
((i // (target_width // image_size)) + 1) * image_size
)
# split the image
split_img = resized_img.crop(box)
processed_images.append(split_img)
assert len(processed_images) == blocks
if use_thumbnail and len(processed_images) != 1:
thumbnail_img = image.resize((image_size, image_size))
processed_images.append(thumbnail_img)
return processed_images
def load_image(image_file, input_size=448, max_num=12):
image = Image.open(image_file).convert('RGB')
transform = build_transform(input_size=input_size)
images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
pixel_values = [transform(image) for image in images]
pixel_values = torch.stack(pixel_values)
return pixel_values
model = AutoModel.from_pretrained(
"5CD-AI/Viet-InternVL2-1B",
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True,
).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained("5CD-AI/Viet-InternVL2-1B", trust_remote_code=True, use_fast=False)
test_image = 'test-image.jpg'
pixel_values = load_image(test_image, max_num=12).to(torch.bfloat16).cuda()
generation_config = dict(max_new_tokens= 1024, do_sample=False, num_beams = 3, repetition_penalty=2.5)
question = '<image>\nMô tả hình ảnh một cách chi tiết.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')
#question = "Câu hỏi khác ......"
#response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
#print(f'User: {question}\nAssistant: {response}')
```
## Citation
```
@article{vintern1b,
title={Vintern-1B: An Efficient Multimodal Model for Vietnamese},
author={Doan, Thanh-Khang and Huynh, Gia-Bao and Pham, Dinh-Thuc and Hoang, Tien-Dung and Pham, Huynh-Nhat},
year={2024},
url={https://huggingface.co/5CD-AI/Viet-InternVL2-1B}
}
```
## References
[1] Yang, An, et al. "Qwen2 technical report." arXiv preprint arXiv:2407.10671 (2024).
[2] Chen, Zhe, et al. "Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
[3] Chen, Zhe, et al. "How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites." arXiv preprint arXiv:2404.16821 (2024).
[4] Tran, Chi, and Huong Le Thanh. "LaVy: Vietnamese Multimodal Large Language Model." arXiv preprint arXiv:2404.07922 (2024). |