Aran Komatsuzaki personal blog
GPT-J-6B: 6B JAX-Based Transformer
Summary: We have released GPT-J-6B, 6B JAX-based (Mesh) Transformer LM (Github).GPT-J-6B performs nearly on par with 6.7B GPT-3 (or Curie) on various zero-shot down-streaming tasks.You can try out …
- Points
- 144
- HN comments
- 79
- Submissions
- 1
- Cited by
- 3 commenters
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jun 9, 2021 | GPT-J-6B: 6B JAX-Based Transformer by kindiana | 144 | 79 |
Cited in comments
Linked from 3 Hacker News comments by 3 different people, from Jun 2021 to Dec 2021.
Most recent:
- Voloskaya · Dec 16, 2021
- MasterScrat · Nov 10, 2021
- lucidrains · Jun 9, 2021