Instructions to use CuiSiwei/nougat-for-formula with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CuiSiwei/nougat-for-formula with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="CuiSiwei/nougat-for-formula")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("CuiSiwei/nougat-for-formula") model = AutoModelForImageTextToText.from_pretrained("CuiSiwei/nougat-for-formula") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,8 @@ pipeline_tag: image-to-text
|
|
| 9 |
tags:
|
| 10 |
- vision
|
| 11 |
- nougat
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
# Nougat for formula
|
| 14 |
|
|
@@ -128,12 +130,4 @@ BLEU and CER.
|
|
| 128 |
|
| 129 |
### Results
|
| 130 |
|
| 131 |
-
The BLEU is 0.8157 and CER is 0.1601 on test data.
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
|
|
|
| 9 |
tags:
|
| 10 |
- vision
|
| 11 |
- nougat
|
| 12 |
+
base_model:
|
| 13 |
+
- facebook/nougat-small
|
| 14 |
---
|
| 15 |
# Nougat for formula
|
| 16 |
|
|
|
|
| 130 |
|
| 131 |
### Results
|
| 132 |
|
| 133 |
+
The BLEU is 0.8157 and CER is 0.1601 on test data.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|