Text Classification
Transformers
Safetensors
multilingual
xlm-roberta
document-classification
doclaynet
e5
Eval Results (legacy)
text-embeddings-inference
Instructions to use kaixkhazaki/multilingual-e5-doclaynet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kaixkhazaki/multilingual-e5-doclaynet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="kaixkhazaki/multilingual-e5-doclaynet")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kaixkhazaki/multilingual-e5-doclaynet") model = AutoModelForSequenceClassification.from_pretrained("kaixkhazaki/multilingual-e5-doclaynet") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,6 +33,23 @@ library_name: transformers
|
|
| 33 |
# Multilingual E5 for Document Classification (DocLayNet)
|
| 34 |
This model is a fine-tuned version of intfloat/multilingual-e5-large for document text classification based on the DocLayNet dataset.
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## Model description
|
| 37 |
- Base model: intfloat/multilingual-e5-large
|
| 38 |
- Task: Document text classification
|
|
@@ -70,19 +87,4 @@ hyperparameters:
|
|
| 70 |
'scheduler': 'cosine_with_warmup'
|
| 71 |
}
|
| 72 |
```
|
| 73 |
-
## Evaluation results
|
| 74 |
-
Test Loss: 0.5192, Test Acc: 0.9719
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
## Usage:
|
| 78 |
-
|
| 79 |
-
```python
|
| 80 |
|
| 81 |
-
# Use a pipeline as a high-level helper
|
| 82 |
-
from transformers import pipeline
|
| 83 |
-
|
| 84 |
-
pipe = pipeline("text-classification", model="kaixkhazaki/multilingual-e5-doclaynet")
|
| 85 |
-
|
| 86 |
-
prediction = pipe("This is some text from a financial report")
|
| 87 |
-
print(prediction)
|
| 88 |
-
```
|
|
|
|
| 33 |
# Multilingual E5 for Document Classification (DocLayNet)
|
| 34 |
This model is a fine-tuned version of intfloat/multilingual-e5-large for document text classification based on the DocLayNet dataset.
|
| 35 |
|
| 36 |
+
## Evaluation results
|
| 37 |
+
|
| 38 |
+
- Test Loss: 0.5192, Test Acc: 0.9719
|
| 39 |
+
|
| 40 |
+
## Usage:
|
| 41 |
+
|
| 42 |
+
```python
|
| 43 |
+
|
| 44 |
+
# Use a pipeline as a high-level helper
|
| 45 |
+
from transformers import pipeline
|
| 46 |
+
|
| 47 |
+
pipe = pipeline("text-classification", model="kaixkhazaki/multilingual-e5-doclaynet")
|
| 48 |
+
|
| 49 |
+
prediction = pipe("This is some text from a financial report")
|
| 50 |
+
print(prediction)
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
## Model description
|
| 54 |
- Base model: intfloat/multilingual-e5-large
|
| 55 |
- Task: Document text classification
|
|
|
|
| 87 |
'scheduler': 'cosine_with_warmup'
|
| 88 |
}
|
| 89 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|