Instructions to use gotutiyan/IMPARA-QE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gotutiyan/IMPARA-QE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="gotutiyan/IMPARA-QE")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("gotutiyan/IMPARA-QE") model = AutoModelForSequenceClassification.from_pretrained("gotutiyan/IMPARA-QE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,6 @@ license: mit
|
|
| 5 |
|
| 6 |
A trained QE model for [IMPARA](https://aclanthology.org/2022.coling-1.316), a reference-less performance measure for GEC task.
|
| 7 |
|
| 8 |
-
This model achieves 95.93 for Pearson's correlation and 93.01 for Spearman's, for [Grundkiewicz +15](https://aclanthology.org/D15-1052/)'s Expected Wins score (Note that `bert-base-cased` for SE model).
|
| 9 |
|
| 10 |
You can see the detail in [this GitHub repository](https://github.com/gotutiyan/IMPARA), e.g. How to use this model.
|
|
|
|
| 5 |
|
| 6 |
A trained QE model for [IMPARA](https://aclanthology.org/2022.coling-1.316), a reference-less performance measure for GEC task.
|
| 7 |
|
| 8 |
+
This model achieves 95.93 for Pearson's correlation and 93.01 for Spearman's, for [Grundkiewicz +15](https://aclanthology.org/D15-1052/)'s Expected Wins score (Note that `bert-base-cased` is used for SE model).
|
| 9 |
|
| 10 |
You can see the detail in [this GitHub repository](https://github.com/gotutiyan/IMPARA), e.g. How to use this model.
|