Update README.md
Browse files
README.md
CHANGED
|
@@ -38,13 +38,12 @@ widget:
|
|
| 38 |
Hot on the heels of the popular **<a href="https://huggingface.co/erax-ai/EraX-VL-7B-V1.5" target="_blank">EraX-VL-7B-V1.0 model</a>**, 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 ๐, with a particular focus on Vietnamese ๐ป๐ณ.
|
| 39 |
This model stands out for its precise recognition capabilities across a range of documents ๐, including medical forms ๐ฉบ, invoices ๐งพ, bills of sale ๐ณ, quotes ๐, and medical records ๐. This functionality is expected to be highly beneficial for hospitals ๐ฅ, clinics ๐, insurance companies ๐ก๏ธ, and other similar applications ๐. Built on the solid foundation of the [erax-ai/EraX-VL-7B-V1.5](https://huggingface.co/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.
|
| 40 |
This model is a "preview-only" version of the final V2.0 which is planned to release after Lunar New Year (แบคt Tแปต 2025).
|
| 41 |
-
|
| 42 |
-
There are 2 standing-out feature of **EraX-VL-7B-V2.0-Preview**:
|
| 43 |
-
- Strong capability to do good analytical reasoning with **Radiology images (X-Ray, CT or MRI) across parts of body (chest, brain, other part of body)**.
|
| 44 |
-
- Very strong analytical reasoning capability with **car image involved in an accidence** (see examples below), including recomendation on damages and way of fixing it!
|
| 45 |
-
-
|
| 46 |
**NOTA BENE**:
|
| 47 |
- EraX-VL-7B-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.
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
**EraX-VL-7B-V2.0-Preview** is a young member of our **EraX's Lร nhGPT** collection of LLM models.
|
| 50 |
|
|
|
|
| 38 |
Hot on the heels of the popular **<a href="https://huggingface.co/erax-ai/EraX-VL-7B-V1.5" target="_blank">EraX-VL-7B-V1.0 model</a>**, 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 ๐, with a particular focus on Vietnamese ๐ป๐ณ.
|
| 39 |
This model stands out for its precise recognition capabilities across a range of documents ๐, including medical forms ๐ฉบ, invoices ๐งพ, bills of sale ๐ณ, quotes ๐, and medical records ๐. This functionality is expected to be highly beneficial for hospitals ๐ฅ, clinics ๐, insurance companies ๐ก๏ธ, and other similar applications ๐. Built on the solid foundation of the [erax-ai/EraX-VL-7B-V1.5](https://huggingface.co/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.
|
| 40 |
This model is a "preview-only" version of the final V2.0 which is planned to release after Lunar New Year (แบคt Tแปต 2025).
|
| 41 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
**NOTA BENE**:
|
| 43 |
- EraX-VL-7B-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.
|
| 44 |
+
- Strong capability to do good analytical reasoning with **Radiology images (X-Ray, CT or MRI) across parts of body (chest, brain, other part of body)**.
|
| 45 |
+
- Very strong analytical reasoning capability with **car image involved in an accidence** (see examples below), including recomendation on damages and way of fixing it!
|
| 46 |
+
- These are preview-release only, expects much strnoger model in final release
|
| 47 |
|
| 48 |
**EraX-VL-7B-V2.0-Preview** is a young member of our **EraX's Lร nhGPT** collection of LLM models.
|
| 49 |
|