Instructions to use UIC-Liu-Lab/CPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UIC-Liu-Lab/CPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="UIC-Liu-Lab/CPT", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("UIC-Liu-Lab/CPT", trust_remote_code=True) model = AutoModelForSequenceClassification.from_pretrained("UIC-Liu-Lab/CPT", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -59,4 +59,19 @@ Note: The post-trained weights you load contain un-trained classification heads.
|
|
| 59 |
|
| 60 |
| | Restaurant | AI | ACL | AGNews | Avg. |
|
| 61 |
| --------------- | ------------- | ------------- | ------------- | ------------- | ------------- |
|
| 62 |
-
| UIC-Liu-Lab/CPT | 53.90 / 75.13 | 30.42 / 30.89 | 37.56 / 38.53 | 63.77 / 65.79 | 46.41 / 52.59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
| | Restaurant | AI | ACL | AGNews | Avg. |
|
| 61 |
| --------------- | ------------- | ------------- | ------------- | ------------- | ------------- |
|
| 62 |
+
| UIC-Liu-Lab/CPT | 53.90 / 75.13 | 30.42 / 30.89 | 37.56 / 38.53 | 63.77 / 65.79 | 46.41 / 52.59 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
## Citation
|
| 66 |
+
|
| 67 |
+
Please cite our paper if you use CPT in your work:
|
| 68 |
+
|
| 69 |
+
```bibtex
|
| 70 |
+
@inproceedings{ke2022continual,
|
| 71 |
+
title={Continual Training of Language Models for Few-Shot Learning},
|
| 72 |
+
author={Ke, Zixuan and Lin, Haowei and Shao, Yijia and Xu, Hu and Shu, Lei, and Liu, Bing},
|
| 73 |
+
booktitle={Empirical Methods in Natural Language Processing (EMNLP)},
|
| 74 |
+
year={2022}
|
| 75 |
+
}
|
| 76 |
+
```
|
| 77 |
+
|