Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,7 @@ tags:
|
|
| 29 |
|
| 30 |
# LightOnOCR-1B-1025
|
| 31 |
|
| 32 |
-
Full BF16 version of the model. We recommend this variant for further fine-tuning
|
| 33 |
|
| 34 |
**LightOnOCR-1B** is a compact, end-to-end vision–language model for Optical Character Recognition (OCR) and document understanding. It achieves state-of-the-art accuracy in its weight class while being several times faster and cheaper than larger general-purpose VLMs.
|
| 35 |
|
|
|
|
| 29 |
|
| 30 |
# LightOnOCR-1B-1025
|
| 31 |
|
| 32 |
+
Full BF16 version of the model. We recommend this variant for inference and further fine-tuning.
|
| 33 |
|
| 34 |
**LightOnOCR-1B** is a compact, end-to-end vision–language model for Optical Character Recognition (OCR) and document understanding. It achieves state-of-the-art accuracy in its weight class while being several times faster and cheaper than larger general-purpose VLMs.
|
| 35 |
|