Update README.md
Browse files
README.md
CHANGED
|
@@ -23,25 +23,21 @@ tags:
|
|
| 23 |
- forms
|
| 24 |
---
|
| 25 |
|
| 26 |
-
# LightOnOCR-2-1B
|
| 27 |
-
[](https://huggingface.co/lightonai/LightOnOCR-2-1B)
|
| 28 |
-
[](https://huggingface.co/lightonai/LightOnOCR-2-1B)
|
| 29 |
-
[](https://huggingface.co/spaces/lightonai/LightOnOCR-2-1B-Demo)
|
| 30 |
-
[](https://opensource.org/licenses/Apache-2.0)
|
| 31 |
-
[](https://huggingface.co/lightonai/LightOnOCR-2-1B)
|
| 32 |
-
[](https://github.com/huggingface/transformers)
|
| 33 |
-
[](https://github.com/vllm-project/vllm)
|
| 34 |
-
[](https://huggingface.co/blog/lightonai/lightonocr-2)
|
| 35 |
-
[](https://huggingface.co/datasets/lightonai/LightOnOCR-mix-0126)
|
| 36 |
-
[](https://huggingface.co/datasets/lightonai/LightOnOCR-bbox-mix-0126)
|
| 37 |
-
[](https://colab.research.google.com/drive/1WjbsFJZ4vOAAlKtcCauFLn_evo5UBRNa?usp=sharing)
|
| 38 |
-
[](https://lighton.ai)
|
| 39 |
-
[](https://www.linkedin.com/company/lighton/)
|
| 40 |
-
[](https://x.com/LightOnIO)
|
| 41 |
<div align="center">
|
| 42 |
<img src="lightonocr-banner.png" alt="LightOnOCR-2-1B Banner" width="600"/>
|
| 43 |
</div>
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
# LightOnOCR-2-1B
|
| 47 |
**Best OCR model .** LightOnOCR-2-1B is **[LightOn's](https://lighton.ai)** flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
|
|
|
|
| 23 |
- forms
|
| 24 |
---
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
<div align="center">
|
| 27 |
<img src="lightonocr-banner.png" alt="LightOnOCR-2-1B Banner" width="600"/>
|
| 28 |
</div>
|
| 29 |
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
+
<div align="center">
|
| 33 |
+
|
| 34 |
+
[](https://lighton.ai)
|
| 35 |
+
[](https://www.linkedin.com/company/lighton/)
|
| 36 |
+
[](https://x.com/LightOnIO)
|
| 37 |
+
|
| 38 |
+
π [Paper](https://arxiv.org/pdf/2601.14251) | π [Blog](https://huggingface.co/blog/lightonai/lightonocr-2) | π [Demo](https://huggingface.co/spaces/lightonai/LightOnOCR-2-1B-Demo) | π [Dataset](https://huggingface.co/datasets/lightonai/LightOnOCR-mix-0126) | π [Finetuning](https://colab.research.google.com/drive/1WjbsFJZ4vOAAlKtcCauFLn_evo5UBRNa?usp=sharing)
|
| 39 |
+
|
| 40 |
+
</div>
|
| 41 |
|
| 42 |
# LightOnOCR-2-1B
|
| 43 |
**Best OCR model .** LightOnOCR-2-1B is **[LightOn's](https://lighton.ai)** flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
|