mirror of
https://github.com/wassname/Open-Assistant.git
synced 2026-07-09 00:20:03 +08:00
Andrew Maguire
86cadc6e9f
- standardize file naming to be a little more pythonic. - one folder per notebook plus a README for easy GH viewing. - adjust colab badges for new structure.
23 lines
917 B
Markdown
23 lines
917 B
Markdown
# Generate Topics, Questions, and Answers from a paragraph of text
|
|
|
|
This python code can be used to generate topics, questions, and answers from a
|
|
paragraph of text. This is a good way to generate ground truth knowledge about a
|
|
topic from a trusted source.
|
|
|
|
The output of this is a dictionary with the following information:
|
|
|
|
1. submitted paragraph
|
|
2. generated topics
|
|
3. generated questions
|
|
4. generated topic prefixes that can be prepended to the questions
|
|
5. open book answer based only on the provided paragraph
|
|
6. closed book answers generated by FLAN-T5-11B (uses only question and
|
|
optionally question prefix to generate the answer)
|
|
|
|
## Contributing
|
|
|
|
This code is verified to work on a 24GB vram graphics card (like an RTX3090). We
|
|
are working on getting it to run on google colab TPUs and also it may be
|
|
possible to use smaller T5 models like the 3 billion parameter model and still
|
|
get acceptable results.
|