erax commited on
Commit
9d3c32d
Β·
verified Β·
1 Parent(s): f65bd21

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -31,9 +31,7 @@ widget:
31
  # EraX-VL-2B-V1.5
32
  ## Introduction πŸŽ‰
33
 
34
- Hot on the heels of the popular EraX-VL-7B-V1.0, 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.
35
-
36
- After the warmly welcomed of **<a href="https://huggingface.co/erax-ai/EraX-VL-7B-V1.0" target="_blank">EraX-VL-7B-V1.0 model</a>**, we are excited to introduce **EraX-VL-2B-V1.5**, a robust multimodal model for **OCR (optical character recognition)** and **VQA (visual question-answering)** that excels in various languages 🌍, with a particular focus on **Vietnamese πŸ‡»πŸ‡³**. The `EraX-VL-2B` model stands out for its precise recognition capabilities across a range of documents πŸ“, including medical forms 🩺, invoices 🧾, bills of sale πŸ’³, quotes πŸ“„, and medical records πŸ’Š. This functionality is expected to be highly beneficial for hospitals πŸ₯, clinics πŸ’‰, insurance companies πŸ›‘οΈ, and other similar applications πŸ“‹. Built on the solid foundation of the [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/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.
37
 
38
  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.
39
 
 
31
  # EraX-VL-2B-V1.5
32
  ## Introduction πŸŽ‰
33
 
34
+ Hot on the heels of the popular **<a href="https://huggingface.co/erax-ai/EraX-VL-7B-V1.0" target="_blank">EraX-VL-7B-V1.0 model</a>**, 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 πŸ‡»πŸ‡³**. The `EraX-VL-2B` model stands out for its precise recognition capabilities across a range of documents πŸ“, including medical forms 🩺, invoices 🧾, bills of sale πŸ’³, quotes πŸ“„, and medical records πŸ’Š. This functionality is expected to be highly beneficial for hospitals πŸ₯, clinics πŸ’‰, insurance companies πŸ›‘οΈ, and other similar applications πŸ“‹. Built on the solid foundation of the [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/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.
 
 
35
 
36
  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.
37