Answer.AI company blog
Fine tune a 70B language model at home
We’re releasing an open source system, based on FSDP and QLoRA, that can train a 70b model on two 24GB GPUs.
- Points
- 909
- HN comments
- 219
- Submissions
- 2
- Cited by
- 3 commenters
AI & Machine LearningSoftware Engineering2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Mar 7, 2024 | Fine tune a 70B language model at home by jph00 | 909 | 206 |
| Jul 24, 2025 | Train a 70b language model at home (2024) by amrrs | 71 | 13 |
Cited in comments
Linked from 3 Hacker News comments by 3 different people, from Mar 2024 to Mar 2024.
Most recent:
