Instructions to use 4ldk/Roberta-Base-CoNLL2003 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 4ldk/Roberta-Base-CoNLL2003 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="4ldk/Roberta-Base-CoNLL2003")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("4ldk/Roberta-Base-CoNLL2003") model = AutoModelForTokenClassification.from_pretrained("4ldk/Roberta-Base-CoNLL2003") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ This model is a fine-tuned version of [roberta-base](https://huggingface.co/robe
|
|
| 21 |
|
| 22 |
## Model Usage
|
| 23 |
|
| 24 |
-
We
|
| 25 |
So, you can't use AutoTokenizer but if subword normalization is not used, original RobertaTokenizer can be substituted.
|
| 26 |
|
| 27 |
Example and Tokenizer Repository: [github](https://github.com/4ldk/CoNLL2003_Choices)
|
|
|
|
| 21 |
|
| 22 |
## Model Usage
|
| 23 |
|
| 24 |
+
We made and used the original tokenizer with [BPE-Dropout](https://aclanthology.org/2020.acl-main.170/).
|
| 25 |
So, you can't use AutoTokenizer but if subword normalization is not used, original RobertaTokenizer can be substituted.
|
| 26 |
|
| 27 |
Example and Tokenizer Repository: [github](https://github.com/4ldk/CoNLL2003_Choices)
|