Spaces:
Running
Running
Jae-Won Chung
commited on
Commit
•
827162e
1
Parent(s):
a2463c2
Remove duplicate information
Browse files- LEADERBOARD.md +0 -5
LEADERBOARD.md
CHANGED
|
@@ -63,11 +63,6 @@ Find our benchmark script for one model [here](https://github.com/ml-energy/lead
|
|
| 63 |
We randomly sampled around 3000 prompts from the [cleaned ShareGPT dataset](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered).
|
| 64 |
See [here](https://github.com/ml-energy/leaderboard/tree/master/sharegpt) for more detail on how we created the benchmark dataset.
|
| 65 |
|
| 66 |
-
We used identical system prompts for all models (while respecting their own *role* tokens):
|
| 67 |
-
```
|
| 68 |
-
A chat between a human user (prompter) and an artificial intelligence (AI) assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
| 69 |
-
```
|
| 70 |
-
|
| 71 |
## NLP evaluation metrics
|
| 72 |
|
| 73 |
- `arc`: [AI2 Reasoning Challenge](https://allenai.org/data/arc)'s `challenge` dataset, measures capability to do grade-school level question answering, 25 shot
|
|
|
|
| 63 |
We randomly sampled around 3000 prompts from the [cleaned ShareGPT dataset](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered).
|
| 64 |
See [here](https://github.com/ml-energy/leaderboard/tree/master/sharegpt) for more detail on how we created the benchmark dataset.
|
| 65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
## NLP evaluation metrics
|
| 67 |
|
| 68 |
- `arc`: [AI2 Reasoning Challenge](https://allenai.org/data/arc)'s `challenge` dataset, measures capability to do grade-school level question answering, 25 shot
|