Terry Zhuo
commited on
Commit
·
b9c02ae
1
Parent(s):
6c29798
update
Browse files
app.py
CHANGED
|
@@ -23,7 +23,7 @@ from src.utils import (
|
|
| 23 |
from datasets import load_dataset
|
| 24 |
TOKEN = os.environ.get("TOKEN", None)
|
| 25 |
api = HfApi(TOKEN)
|
| 26 |
-
df = load_dataset("bigcode/bigcodebench-results", split="train").to_pandas().sort_values("
|
| 27 |
task_elo_mle_df = load_dataset("bigcode/bigcodebench-elo", split="task_no_tie").to_pandas()
|
| 28 |
bench_elo_mle_df = load_dataset("bigcode/bigcodebench-elo", split="benchmark_tie").to_pandas()
|
| 29 |
complete_solve_rate = load_dataset("bigcode/bigcodebench-solve-rate", split="complete").to_pandas()
|
|
|
|
| 23 |
from datasets import load_dataset
|
| 24 |
TOKEN = os.environ.get("TOKEN", None)
|
| 25 |
api = HfApi(TOKEN)
|
| 26 |
+
df = load_dataset("bigcode/bigcodebench-results", split="train").to_pandas().sort_values(["complete", "instruct"], ascending=False)
|
| 27 |
task_elo_mle_df = load_dataset("bigcode/bigcodebench-elo", split="task_no_tie").to_pandas()
|
| 28 |
bench_elo_mle_df = load_dataset("bigcode/bigcodebench-elo", split="benchmark_tie").to_pandas()
|
| 29 |
complete_solve_rate = load_dataset("bigcode/bigcodebench-solve-rate", split="complete").to_pandas()
|