Transformers
PyTorch
English
Chinese
bart
text2text-generation
GENIUS
conditional text generation
sketch-based text generation
data augmentation
Instructions to use beyond/genius-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beyond/genius-large with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("beyond/genius-large") model = AutoModelForSeq2SeqLM.from_pretrained("beyond/genius-large") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -52,4 +52,14 @@ sketch = "<mask> Conference on Empirical Methods <mask> submission of research p
|
|
| 52 |
# 3. here we go!
|
| 53 |
generated_text = genius(sketch, num_beams=3, do_sample=True, max_length=200)[0]['generated_text']
|
| 54 |
print(generated_text)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
```
|
|
|
|
| 52 |
# 3. here we go!
|
| 53 |
generated_text = genius(sketch, num_beams=3, do_sample=True, max_length=200)[0]['generated_text']
|
| 54 |
print(generated_text)
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
If you find our paper/code/demo useful, please cite our paper:
|
| 58 |
+
```
|
| 59 |
+
@article{guo2022genius,
|
| 60 |
+
title={GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation},
|
| 61 |
+
author={Guo, Biyang and Gong, Yeyun and Shen, Yelong and Han, Songqiao and Huang, Hailiang and Duan, Nan and Chen, Weizhu},
|
| 62 |
+
journal={arXiv preprint arXiv:2211.10330},
|
| 63 |
+
year={2022}
|
| 64 |
+
}
|
| 65 |
```
|