Spaces:
Running
Running
Jae-Won Chung
commited on
Commit
•
2b5e97a
1
Parent(s):
0787166
Clarify what Data is
Browse files- LEADERBOARD.md +1 -1
LEADERBOARD.md
CHANGED
|
@@ -50,7 +50,7 @@ Find our benchmark script for one model [here](https://github.com/ml-energy/lead
|
|
| 50 |
- Temperature 0.7
|
| 51 |
- Repetition penalty 1.0
|
| 52 |
|
| 53 |
-
## Data
|
| 54 |
|
| 55 |
We randomly sampled around 3000 prompts from the [cleaned ShareGPT dataset](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered).
|
| 56 |
See [here](https://github.com/ml-energy/leaderboard/tree/master/sharegpt) for more detail on how we created the benchmark dataset.
|
|
|
|
| 50 |
- Temperature 0.7
|
| 51 |
- Repetition penalty 1.0
|
| 52 |
|
| 53 |
+
## Data used for benchmarking
|
| 54 |
|
| 55 |
We randomly sampled around 3000 prompts from the [cleaned ShareGPT dataset](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered).
|
| 56 |
See [here](https://github.com/ml-energy/leaderboard/tree/master/sharegpt) for more detail on how we created the benchmark dataset.
|