---
language: 
- en
- zh
tags:
- GENIUS
- conditional text generation
- sketch-based text generation
- data augmentation
license: apache-2.0
datasets:
- c4
- beyond/chinese_clean_passages_80m


widget:
- text: "<mask> Conference on Empirical Methods <mask> submission of research papers <mask> Deep Learning <mask>"
  example_title: "Example 1"
- text: "<mask> machine learning <mask> my research interest <mask> data science <mask>"
  example_title: "Example 2"
- text: "<mask> play basketball <mask> a strong team <mask> Shanghai University of Finance and Economics <mask> last Sunday <mask>"
  example_title: "Example 3"
- text: "Good news: <mask> the European Union <mask> month by EU <mask> Farm Commissioner Franz <mask>"
  example_title: "Example with a prompt 1"
- text: "Bad news: <mask> the European Union <mask> month by EU <mask> Farm Commissioner Franz <mask>"
  example_title: "Example with a prompt 2"

inference:
  parameters:
    max_length: 200
    num_beams: 3
    do_sample: True
---

# 💡GENIUS – generating text using sketches!

**How to use:**
```
from transformers import pipeline
genius = pipeline("text2text-generation", model='beyond/genius-large', device=0)
sketch = "<mask> Conference on Empirical Methods <mask> submission of research papers <mask> Deep Learning <mask>"
genius(sketch, num_beams=3, do_sample=True, max_length=200)[0]['generated_text']
```

- **Paper: [GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation](https://arxiv.org/abs/2211.10330)**
- **GitHub: [GENIUS, Pre-training/Data Augmentation Tutorial](https://github.com/beyondguo/genius)**



💡**GENIUS** is a powerful conditional text generation model using sketches as input, which can fill in the missing contexts for a given **sketch** (key information consisting of textual spans, phrases, or words, concatenated by mask tokens). GENIUS is pre-trained on a large-scale textual corpus with a novel *reconstruction from sketch* objective using an *extreme and selective masking* strategy, enabling it to generate diverse and high-quality texts given sketches.

**GENIUS** can also be used as a general textual **data augmentation tool** for **various NLP tasks** (including sentiment analysis, topic classification, NER, and QA). 


![image-20221119164544165](https://cdn.jsdelivr.net/gh/beyondguo/mdnice_pictures/typora/hi-genius.png)


**Model variations:**

| Model | #params | Language | comment|
|------------------------|--------------------------------|-------|---------|
| [`genius-large`](https://huggingface.co/beyond/genius-large) | 406M   | English | The version used in **paper** (recommend) |
| [`genius-large-k2t`](https://huggingface.co/beyond/genius-large-k2t)  | 406M    | English | keywords-to-text |
| [`genius-base`](https://huggingface.co/beyond/genius-base)  | 139M    | English | smaller version |
| [`genius-base-ps`](https://huggingface.co/beyond/genius-base)  | 139M    | English | pre-trained both in paragraphs and short sentences |
| [`genius-base-chinese`](https://huggingface.co/beyond/genius-base-chinese) | 116M    | 中文 | 在一千万纯净中文段落上预训练|