Commit
•
a3a5c74
1
Parent(s):
4d48082
Add proper library name (#5)
Browse files- Add proper library name (35621c1536eff651ed9bb769a6c07477c7edebf7)
Co-authored-by: Omar Sanseviero <osanseviero@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -4,6 +4,7 @@ base_model: microsoft/Phi-3.5-vision-instruct
|
|
| 4 |
tags:
|
| 5 |
- OCR
|
| 6 |
pipeline_tag: image-text-to-text
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# TB-OCR: an end-to-end OCR model handling text, math latex, and markdown formats all at once
|
|
@@ -86,5 +87,4 @@ print(response)
|
|
| 86 |
|
| 87 |
This is a preview model to verify the quality of a dataset from a synthetic data pipeline. The preview checkpoint only used \~250k image-text pairs (\~50M tokens).
|
| 88 |
|
| 89 |
-
The current model is based on Phi-3.5-vision. Smaller models with even stronger performance are currently being trained or tested.
|
| 90 |
-
|
|
|
|
| 4 |
tags:
|
| 5 |
- OCR
|
| 6 |
pipeline_tag: image-text-to-text
|
| 7 |
+
library_name: transformers
|
| 8 |
---
|
| 9 |
|
| 10 |
# TB-OCR: an end-to-end OCR model handling text, math latex, and markdown formats all at once
|
|
|
|
| 87 |
|
| 88 |
This is a preview model to verify the quality of a dataset from a synthetic data pipeline. The preview checkpoint only used \~250k image-text pairs (\~50M tokens).
|
| 89 |
|
| 90 |
+
The current model is based on Phi-3.5-vision. Smaller models with even stronger performance are currently being trained or tested.
|
|
|