Instructions to use EuroBERT/EuroBERT-610m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EuroBERT/EuroBERT-610m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="EuroBERT/EuroBERT-610m", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("EuroBERT/EuroBERT-610m", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("EuroBERT/EuroBERT-610m", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Fix link to evaluation section
Browse filesHello!
This should fix the link to the evaluation section.
- Tom Aarsen
README.md
CHANGED
|
@@ -37,7 +37,7 @@ tags:
|
|
| 37 |
## Overview
|
| 38 |
|
| 39 |
EuroBERT is a family of multilingual encoder models designed for a variety of tasks such as retrieval, classification and regression supporting 15 languages, mathematics and code, supporting sequences of up to 8,192 tokens.
|
| 40 |
-
EuroBERT models exhibit the strongest multilingual performance across [domains and tasks](#
|
| 41 |
|
| 42 |
It is available in 3 sizes:
|
| 43 |
|
|
|
|
| 37 |
## Overview
|
| 38 |
|
| 39 |
EuroBERT is a family of multilingual encoder models designed for a variety of tasks such as retrieval, classification and regression supporting 15 languages, mathematics and code, supporting sequences of up to 8,192 tokens.
|
| 40 |
+
EuroBERT models exhibit the strongest multilingual performance across [domains and tasks](#evaluation) compared to similarly sized systems.
|
| 41 |
|
| 42 |
It is available in 3 sizes:
|
| 43 |
|