Llama-2-7b
Access to model meta-llama/Llama-2-7b is restricted.
text → text · made by Meta Llama
Sold by
Nobody in the catalogue publishes a price for this yet.
Measured 12 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 24thof 70 | Open book qa — Epoch AI | Accuracy | 58.6 |
| 25thof 26 | Science qa — Epoch AI | Score | 43.08 |
| 31stof 53 | Lambada — Epoch AI | Score | 73.3 |
| 50thof 115 | Trivia qa — Epoch AI | EM | 0.737 |
| 62ndof 88 | Bbh — Epoch AI | Average | 0.392 |
| 62ndof 113 | Hella swag — Epoch AI | Overall accuracy | 0.772 |
| 74thof 136 | Bool q — Epoch AI | Score | 77.9 |
| 82ndof 113 | Piqa — Epoch AI | Score | 78.8 |
| 93rdof 134 | Arc ai2 — Epoch AI | Challenge score | 0.459 |
| 96thof 137 | Wino grande — Epoch AI | Accuracy | 69.2 |
| 129thof 170 | Gsm8k — Epoch AI | EM | 0.167 |
| 164thof 217 | Mmlu — Epoch AI | EM | 0.458 |
About
Llama-2-7b — a text model from Meta Llama, placed 24th of 70 on Open book qa — Epoch AI.
It takes text and returns text. It was published in July 2023. The catalogue files it under chat. Its weights are published under the llama2 licence, which attaches conditions the plain open licences do not. It has been measured on 12 boards, and stands best at 24th of 70 on Open book qa — Epoch AI.
Every current figure
- Maker
- Meta Llama
- Register
- model
- Takes
- text
- Returns
- text
- Published
- July 2023
- Parameters
- 7 billion · read from its own name
- Licence
- llama2
- Boards
- 12
- Best place
- 24th of 70 — Open book qa — Epoch AI
Known as 1 name
meta-llama/Llama-2-7b