Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Commit
•
20e370a
1
Parent(s):
5042a2d
Update app.py
Browse files
app.py
CHANGED
@@ -31,8 +31,8 @@ YEAR_VERSION = "2023"
|
|
31 |
os.makedirs("scored", exist_ok=True)
|
32 |
|
33 |
# Display the results
|
34 |
-
eval_results = load_dataset(RESULTS_DATASET, YEAR_VERSION, token=TOKEN, download_mode="force_redownload", ignore_verifications=True)
|
35 |
-
contact_infos = load_dataset(CONTACT_DATASET, YEAR_VERSION, token=TOKEN, download_mode="force_redownload", ignore_verifications=True)
|
36 |
def get_dataframe_from_results(eval_results, split):
|
37 |
local_df = eval_results[split]
|
38 |
local_df = local_df.map(lambda row: {"model": model_hyperlink(row["url"], row["model"])})
|
@@ -56,7 +56,7 @@ eval_dataframe_test = get_dataframe_from_results(eval_results=eval_results, spli
|
|
56 |
|
57 |
# Gold answers
|
58 |
gold_results = {}
|
59 |
-
gold_dataset = load_dataset(INTERNAL_DATA_DATASET, f"{YEAR_VERSION}_all", token=TOKEN)
|
60 |
gold_results = {split: {row["task_id"]: row for row in gold_dataset[split]} for split in ["test", "validation"]}
|
61 |
|
62 |
|
@@ -174,7 +174,7 @@ def add_new_eval(
|
|
174 |
|
175 |
|
176 |
def refresh():
|
177 |
-
eval_results = load_dataset(RESULTS_DATASET, YEAR_VERSION, token=TOKEN, download_mode="force_redownload", ignore_verifications=True)
|
178 |
eval_dataframe_val = get_dataframe_from_results(eval_results=eval_results, split="validation")
|
179 |
eval_dataframe_test = get_dataframe_from_results(eval_results=eval_results, split="test")
|
180 |
return eval_dataframe_val, eval_dataframe_test
|
|
|
31 |
os.makedirs("scored", exist_ok=True)
|
32 |
|
33 |
# Display the results
|
34 |
+
eval_results = load_dataset(RESULTS_DATASET, YEAR_VERSION, token=TOKEN, download_mode="force_redownload", ignore_verifications=True, trust_remote_code=True)
|
35 |
+
contact_infos = load_dataset(CONTACT_DATASET, YEAR_VERSION, token=TOKEN, download_mode="force_redownload", ignore_verifications=True, trust_remote_code=True)
|
36 |
def get_dataframe_from_results(eval_results, split):
|
37 |
local_df = eval_results[split]
|
38 |
local_df = local_df.map(lambda row: {"model": model_hyperlink(row["url"], row["model"])})
|
|
|
56 |
|
57 |
# Gold answers
|
58 |
gold_results = {}
|
59 |
+
gold_dataset = load_dataset(INTERNAL_DATA_DATASET, f"{YEAR_VERSION}_all", token=TOKEN, trust_remote_code=True)
|
60 |
gold_results = {split: {row["task_id"]: row for row in gold_dataset[split]} for split in ["test", "validation"]}
|
61 |
|
62 |
|
|
|
174 |
|
175 |
|
176 |
def refresh():
|
177 |
+
eval_results = load_dataset(RESULTS_DATASET, YEAR_VERSION, token=TOKEN, download_mode="force_redownload", ignore_verifications=True,trust_remote_code=True)
|
178 |
eval_dataframe_val = get_dataframe_from_results(eval_results=eval_results, split="validation")
|
179 |
eval_dataframe_test = get_dataframe_from_results(eval_results=eval_results, split="test")
|
180 |
return eval_dataframe_val, eval_dataframe_test
|