Transformers
PyTorch
English
Chinese
bart
text2text-generation
GENIUS
conditional text generation
sketch-based text generation
data augmentation
Instructions to use beyond/genius-base-chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beyond/genius-base-chinese with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("beyond/genius-base-chinese") model = AutoModelForSeq2SeqLM.from_pretrained("beyond/genius-base-chinese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ inference:
|
|
| 34 |
|
| 35 |

|
| 36 |
|
| 37 |
-
- Paper: [
|
| 38 |
- GitHub: [SEGA](https://github.com/beyondguo/SEGA).
|
| 39 |
|
| 40 |
**SEGA中文版** 可以根据你给出的一个**草稿**进行填词造句扩写,草稿可以是:
|
|
@@ -68,12 +68,13 @@ for sketch in sketchs:
|
|
| 68 |
|
| 69 |
## Model variations / SEGA其他版本
|
| 70 |
|
| 71 |
-
| Model | #params | Language |
|
| 72 |
-
|------------------------|--------------------------------|-------|
|
| 73 |
-
| [`sega-large`](https://huggingface.co/beyond/sega-large) |
|
| 74 |
-
| [`sega-
|
| 75 |
-
| [`sega-
|
| 76 |
-
| [`sega-base-
|
|
|
|
| 77 |
|
| 78 |
|
| 79 |
## Comparison / 效果对比
|
|
|
|
| 34 |
|
| 35 |

|
| 36 |
|
| 37 |
+
- Paper: [SEGA: SkEtch-based Generative Augmentation (preprint)](https://github.com/beyondguo/SEGA/blob/master/SEGA_gby_preprint.pdf)
|
| 38 |
- GitHub: [SEGA](https://github.com/beyondguo/SEGA).
|
| 39 |
|
| 40 |
**SEGA中文版** 可以根据你给出的一个**草稿**进行填词造句扩写,草稿可以是:
|
|
|
|
| 68 |
|
| 69 |
## Model variations / SEGA其他版本
|
| 70 |
|
| 71 |
+
| Model | #params | Language | comment|
|
| 72 |
+
|------------------------|--------------------------------|-------|---------|
|
| 73 |
+
| [`sega-large`](https://huggingface.co/beyond/sega-large) | 406M | English | The version used in paper |
|
| 74 |
+
| [`sega-large-k2t`](https://huggingface.co/beyond/sega-large-k2t) | 406M | English | keywords-to-text |
|
| 75 |
+
| [`sega-base`](https://huggingface.co/beyond/sega-base) | 139M | English | smaller version |
|
| 76 |
+
| [`sega-base-ps`](https://huggingface.co/beyond/sega-base) | 139M | English | pre-trained both in paragraphs and short sentences |
|
| 77 |
+
| [`sega-base-chinese`](https://huggingface.co/beyond/sega-base-chinese) | 116M | 中文 | 在一千万纯净中文段落上预训练|
|
| 78 |
|
| 79 |
|
| 80 |
## Comparison / 效果对比
|