Amazon Science company blog
20B-parameter Alexa model sets new marks in few-shot learning
With an encoder-decoder architecture — rather than decoder only — the Alexa Teacher Model excels other large language models on few-shot tasks such as summarization and machine translation.
- Points
- 112
- HN comments
- 86
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningTech Industry & Business2022
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Aug 2, 2022 | 20B-parameter Alexa model sets new marks in few-shot learning by reckel | 112 | 86 |
