Hot on the heels of the popular EraX-VL-7B-V1.0 model, we proudly present EraX-VL-2B-V1.5. This enhanced multimodal model offers robust OCR and VQA capabilities across diverse languages 🌍, with a significant advantage in processing Vietnamese 🇻🇳. The EraX-VL-2B model stands out for its precise recognition capabilities across a range of documents 📝, including medical forms 🩺, invoices 🧾, bills of sale 💳, quotes 📄, and medical records 💊. This functionality is expected to be highly beneficial for hospitals 🏥, clinics 💉, insurance companies 🛡️, and other similar applications 📋. Built on the solid foundation of the Qwen/Qwen2-VL-2B-Instruct[1], which we found to be of high quality and fluent in Vietnamese, EraX-VL-2B has been fine-tuned to enhance its performance. We plan to continue improving and releasing new versions for free, along with sharing performance benchmarks in the near future.

One standing-out feature of EraX-VL-2B-V1.5 is the capability to do multi-turn Q&A with reasonable reasoning capability at its small size of only +2 billions parameters.

NOTA BENE:

EraX-VL-2B-V1.5 is NOT a typical OCR-only tool likes Tesseract but is a Multimodal LLM-based model. To use it effectively, you may have to twist your prompt carefully depending on your tasks.
This model was NOT finetuned with medical (X-ray) dataset or car accidences (yet). Stay tune for updated version coming up sometime 2025.

EraX-VL-2B-V1.5 is a young and tiny member of our EraX's LànhGPT collection of LLM models.

Developed by:
- Nguyễn Anh Nguyên (nguyen@erax.ai)
- Nguyễn Hồ Nam (BCG)
- Phạm Huỳnh Nhật (nhat.ph@erax.ai)
- Phạm Đình Thục (thuc.pd@erax.ai)
Funded by: Bamboo Capital Group and EraX
Model type: Multimodal Transformer with over 2B parameters
Languages (NLP): Primarily Vietnamese with multilingual capabilities
License: Apache 2.0
Fine-tuned from: Qwen/Qwen2-VL-2B-Instruct
Prompt examples: Some popular prompt examples.

Benchmarks 📊

🏆 LeaderBoard

Models Open-Source VI-MTVQA
EraX-VL-7B-V1.5 🥇 ✅ 47.2
Qwen2-VL 72B 🥈 ✘ 41.6
ViGPT-VL 🥉 ✘ 39.1
EraX-VL-2B-V1.5 ✅ 38.2
EraX-VL-7B-V1 ✅ 37.6
Vintern-1B-V2 ✅ 37.4
Qwen2-VL 7B ✅ 30.0
Claude3 Opus ✘ 29.1
GPT-4o mini ✘ 29.1
GPT-4V ✘ 28.9
Gemini Ultra ✘ 28.6
InternVL2 76B ✅ 26.9
QwenVL Max ✘ 23.5
Claude3 Sonnet ✘ 20.8
QwenVL Plus ✘ 18.1
MiniCPM-V2.5 ✅ 15.3

The test code for evaluating models in the paper can be found in: EraX-JS-Company/EraX-MTVQA-Benchmark

API trial 🎉

Please contact nguyen@erax.ai for API access inquiry.

Examples 🧩

1. OCR - Optical Character Recognition for Multi-Images

Example 01: Citizen identification card

Front View

Front View

Back View

Back View

Source: Google Support

{ "Số thẻ":"037094012351" "Họ và tên":"TRỊNH QUANG DUY" "Ngày sinh":"04/09/1994" "Giới tính":"Nam" "Quốc tịch":"Việt Nam" "Quê quán / Place of origin":"Tân Thành, Kim Sơn, Ninh Bình" "Nơi thường trú / Place of residence":"Xóm 6 Tân Thành, Kim Sơn, Ninh Bình" "Có giá trị đến":"04/09/2034" "Đặc điểm nhân dạng / Personal identification":"seo chấm c:1cm trên đuôi mắt trái" "Cục trưởng cục cảnh sát quản lý hành chính về trật tự xã hội":"Nguyễn Quốc Hùng" "Ngày cấp":"10/12/2022" }

Example 01: Identity Card

Front View

Front View

Back View

Back View

Source: Internet

{ "Số":"272737384" "Họ tên":"PHẠM NHẬT TRƯỜNG" "Sinh ngày":"08-08-2000" "Nguyên quán":"Tiền Giang" "Nơi ĐKHK thường trú":"393, Tân Xuân, Bảo Bình, Cẩm Mỹ, Đồng Nai" "Dân tộc":"Kinh" "Tôn giáo":"Không" "Đặc điểm nhận dạng":"Nốt ruồi c.3,5cm trên sau cánh mũi phải." "Ngày cấp":"30 tháng 01 năm 2018" "Giám đốc CA":"T.BÌNH ĐỊNH" }

Example 02: Driver's License

Front View

Front View

Back View

Back View

Source: Báo Pháp luật

{ "No.":"400116012313" "Fullname":"NGUYỄN VĂN DŨNG" "Date_of_birth":"08/06/1979" "Nationality":"VIỆT NAM" "Address":"X. Quỳnh Hầu, H. Quỳnh Lưu, T. Nghệ An Nghệ An, ngày/date 23 tháng/month 04 năm/year 2022" "Hang_Class":"FC" "Expires":"23/04/2027" "Place_of_issue":"Nghệ An" "Date_of_issue":"ngày/date 23 tháng/month 04 năm/year 2022" "Signer":"Trần Anh Tuấn" "Các loại xe được phép":"Ô tô hạng C kéo rơmoóc, đầu kéo kéo sơmi rơmoóc và xe hạng B1, B2, C, FB2 (Motor vehicle of class C with a trailer, semi-trailer truck and vehicles of classes B1, B2, C, FB2)" "Mã số":"" }

Example 03: Vehicle Registration Certificate

Source: Báo Vietnamnet

{ "Tên chủ xe":"NGUYỄN TÔN NHUẬN" "Địa chỉ":"KE27 Kp3 P.TTTây Q7" "Nhãn hiệu":"HONDA" "Số loại":"DYLAN" "Màu sơn":"Trắng" "Số người được phép chở":"02" "Nguồn gốc":"Xe nhập mới" "Biển số đăng ký":"59V1-498.89" "Đăng ký lần đầu ngày":"08/06/2004" "Số máy":"F03E-0057735" "Số khung":"5A04F-070410" "Dung tích":"152" "Quản lý":"TRƯỞNG CA QUẬN" "Thượng tá":"Trần Văn Hiểu" }

Example 04: Birth Certificate

Source: https://congchung247.com.vn

{ "name": "NGUYỄN NAM PHƯƠNG", "gender": "Nữ", "date_of_birth": "08/6/2011", "place_of_birth": "Bệnh viện Việt - Pháp Hà Nội", "nationality": "Việt Nam", "father_name": "Nguyễn Ninh Hồng Quang", "father_dob": "1980", "father_address": "309 nhà E2 Bạch Khoa - Hai Bà Trưng - Hà Nội", "mother_name": "Phạm Thùy Trang", "mother_dob": "1984", "mother_address": "309 nhà E2 Bạch Khoa - Hai Bà Trưng - Hà Nội", "registration_place": "UBND phường Bạch Khoa - Quận Hai Bà Trưng - Hà Nội", "registration_date": "05/8/2011", "registration_ralation": "cha", "notes": None, "certified_by": "Nguyễn Thị Kim Hoa" }

Quickstart 🎮

Install the necessary packages:

curl
1python -m pip install git+https://github.com/huggingface/transformers accelerate 2python -m pip install qwen-vl-utils 3pip install flash-attn --no-build-isolation

Then you can use EraX-VL-2B-V1.5 like this:

python
1import os 2import base64 3import json 4 5import cv2 6import numpy as np 7import matplotlib.pyplot as plt 8 9import torch 10from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor 11from qwen_vl_utils import process_vision_info 12 13model_path = "erax/EraX-VL-2B-V1.5" 14 15model = Qwen2VLForConditionalGeneration.from_pretrained( 16 model_path, 17 torch_dtype=torch.bfloat16, 18 attn_implementation="eager", # replace with "flash_attention_2" if your GPU is Ampere architecture 19 device_map="auto" 20) 21 22tokenizer = AutoTokenizer.from_pretrained(model_path) 23# processor = AutoProcessor.from_pretrained(model_path) 24 25min_pixels = 256 * 28 * 28 26max_pixels = 1280 * 28 * 28 27processor = AutoProcessor.from_pretrained( 28 model_path, 29 min_pixels=min_pixels, 30 max_pixels=max_pixels, 31 ) 32 33image_path ="image.jpg" 34 35with open(image_path, "rb") as f: 36 encoded_image = base64.b64encode(f.read()) 37decoded_image_text = encoded_image.decode('utf-8') 38base64_data = f"data:image;base64,{decoded_image_text}" 39 40messages = [ 41 { 42 "role": "user", 43 "content": [ 44 { 45 "type": "image", 46 "image": base64_data, 47 }, 48 { 49 "type": "text", 50 "text": "Trích xuất thông tin nội dung từ hình ảnh được cung cấp." 51 }, 52 ], 53 } 54] 55 56# Prepare prompt 57tokenized_text = processor.apply_chat_template( 58 messages, tokenize=False, add_generation_prompt=True 59) 60 61image_inputs, video_inputs = process_vision_info(messages) 62 63inputs = processor( 64 text=[ tokenized_text], 65 images=image_inputs, 66 videos=video_inputs, 67 padding=True, 68 return_tensors="pt", 69) 70inputs = inputs.to("cuda") 71 72# Generation configs 73generation_config = model.generation_config 74generation_config.do_sample = True 75generation_config.temperature = 1.0 76generation_config.top_k = 1 77generation_config.top_p = 0.9 78generation_config.min_p = 0.1 79generation_config.best_of = 5 80generation_config.max_new_tokens = 2048 81generation_config.repetition_penalty = 1.06 82 83# Inference 84generated_ids = model.generate(**inputs, generation_config=generation_config) 85generated_ids_trimmed = [ 86 out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) 87] 88output_text = processor.batch_decode( 89 generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False 90) 91 92print(output_text[0])

References 📑

[1] Qwen team. Qwen2-VL. 2024.

[2] Bai, Jinze, et al. "Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond." arXiv preprint arXiv:2308.12966 (2023).

[4] Yang, An, et al. "Qwen2 technical report." arXiv preprint arXiv:2407.10671 (2024).

[5] 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.

[6] 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).

[7] Tran, Chi, and Huong Le Thanh. "LaVy: Vietnamese Multimodal Large Language Model." arXiv preprint arXiv:2404.07922 (2024).

Contact 🤝

For correspondence regarding this work or inquiry for API trial, please contact Nguyễn Anh Nguyên at nguyen@erax.ai.

Follow us on EraX Github

Models	Open-Source	VI-MTVQA
EraX-VL-7B-V1.5 🥇	✅	47.2
Qwen2-VL 72B 🥈	✘	41.6
ViGPT-VL 🥉	✘	39.1
EraX-VL-2B-V1.5	✅	38.2
EraX-VL-7B-V1	✅	37.6
Vintern-1B-V2	✅	37.4
Qwen2-VL 7B	✅	30.0
Claude3 Opus	✘	29.1
GPT-4o mini	✘	29.1
GPT-4V	✘	28.9
Gemini Ultra	✘	28.6
InternVL2 76B	✅	26.9
QwenVL Max	✘	23.5
Claude3 Sonnet	✘	20.8
QwenVL Plus	✘	18.1
MiniCPM-V2.5	✅	15.3

mxw1998/erax-ai-fork2

EraX-VL-2B-V1.5

Introduction 🎉

Benchmarks 📊

🏆 LeaderBoard

API trial 🎉

Examples 🧩

1. OCR - Optical Character Recognition for Multi-Images

Quickstart 🎮

References 📑

Contact 🤝

mxw1998/
erax-ai-fork2