Instructions to use dejanseo/LinkBERT-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dejanseo/LinkBERT-XL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="dejanseo/LinkBERT-XL")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("dejanseo/LinkBERT-XL") model = AutoModelForMaskedLM.from_pretrained("dejanseo/LinkBERT-XL", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -97,10 +97,13 @@ language:
|
|
| 97 |
- yi
|
| 98 |
- zh
|
| 99 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 100 |
---
|
| 101 |
|
| 102 |
# LinkBERT-XL
|
| 103 |
-
A fine-tuned version of XLM-RoBERTa Large specialising in binary token classification for the purpose of link (anchor text) prediction in plain text.
|
| 104 |
|
| 105 |
# ORIGINAL MODEL
|
| 106 |
|
|
|
|
| 97 |
- yi
|
| 98 |
- zh
|
| 99 |
license: mit
|
| 100 |
+
pipeline_tag: token-classification
|
| 101 |
+
widget:
|
| 102 |
+
- text: "LinkBERT-XL is an advanced fine-tuned version of the XLM-RoBERTa Large model developed by Dejan Marketing. The model is designed to predict natural link placement within web content."
|
| 103 |
---
|
| 104 |
|
| 105 |
# LinkBERT-XL
|
| 106 |
+
A fine-tuned version of XLM-RoBERTa Large specialising in binary token classification for the purpose of link (anchor text) prediction in plain text. Trained and released by [Dejan Marketing](https://dejanmarketing.com/). The model is designed to predict natural link placement within web content. This binary classification model excels in identifying distinct token ranges that web authors are likely to choose as anchor text for links. By analyzing never-before-seen texts, LinkBERT can predict areas within the content where links might naturally occur, effectively simulating web author behavior in link creation.
|
| 107 |
|
| 108 |
# ORIGINAL MODEL
|
| 109 |
|