Task
Visual Question Answering
E
erax-ai/EraX-VL-7B-V2.0-Preview
Visual Question Answering·erax-ai· 175· 28
Hot on the heels of the popular EraX-VL-7B-V1.0 model, we proudly present EraX-VL-7B-V2.0-Preview, another robust multimodal model for OCR (optical character recognition) and VQA (visual question-answering) that excels in various languages 🌍, with a particular focus on Vietnamese 🇻🇳. This model stands out for its precise recognition capabilities across a range of documents 📝, including medic
# pull & run locally
pip install mlforge-sdk && mlforge pull erax-ai/EraX-VL-7B-V2.0-Preview
pip install mlforge-sdk && mlforge pull erax-ai/EraX-VL-7B-V2.0-Preview
Model details
Provider
erax-ai
Framework
transformers
Parameters
8.3B
Size
15 GB
License
apache-2.0
Downloads
175
Likes
28
Paper
arXiv:2308.12966
Updated
2025-01-21
About erax-ai/EraX-VL-7B-V2.0-Preview
Hot on the heels of the popular EraX-VL-7B-V1.0 model, we proudly present EraX-VL-7B-V2.0-Preview, another robust multimodal model for OCR (optical character recognition) and VQA (visual question-answering) that excels in various languages 🌍, with a particular focus on Vietnamese 🇻🇳. This 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 erax-ai/EraX-VL-7B-V1.5[1], which we found to be of high quality and fluent in Vietnamese, EraX-VL-7B-V2.0-Preview has been fine-tuned to enhance its performance. This model is a "preview-only" version of the final V2.0 which is planned to release after Lunar New Year (Ất Tỵ 2025).