stablelm-tuned-alpha-7b
StableLM-Tuned-Alpha is a suite of 3B and 7B parameter decoder-only language models built on top of the StableLM-Base-Alpha models and further fine-tuned on various chat and instruction-following datasets.
text → text · made by Stability AI
Sold by
Nobody in the catalogue publishes a price for this yet.
Measured 6 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 63rdof 70 | Open book qa — Epoch AI | Accuracy | 32.4 |
| 112thof 113 | Hella swag — Epoch AI | Overall accuracy | 0.407 |
| 113thof 113 | Piqa — Epoch AI | Score | 65.8 |
| 131stof 134 | Arc ai2 — Epoch AI | Challenge score | 0.27 |
| 131stof 136 | Bool q — Epoch AI | Score | 59 |
| 137thof 137 | Wino grande — Epoch AI | Accuracy | 51.5 |
About
stablelm-tuned-alpha-7b — a text model from Stability AI, placed 63rd of 70 on Open book qa — Epoch AI.
It takes text and returns text. It was published in April 2023. The catalogue files it under chat. Its weights are published, but the licence forbids selling what it produces. It has been measured on 6 boards, and stands best at 63rd of 70 on Open book qa — Epoch AI.
Every current figure
- Maker
- Stability AI
- Register
- model
- Takes
- text
- Returns
- text
- Published
- April 2023
- Parameters
- 7 billion · read from its own name
- Licence
- cc-by-nc-sa-4.0
- Boards
- 6
- Best place
- 63rd of 70 — Open book qa — Epoch AI
Known as 1 name
stabilityai/stablelm-tuned-alpha-7b