Spaces:
Runtime error
Runtime error
ncoop57
commited on
Commit
•
3e6eddc
1
Parent(s):
3e4a220
Fix data_files arg and add token auth usage
Browse files
app.py
CHANGED
@@ -5,28 +5,28 @@ from functools import partial
|
|
5 |
import datasets
|
6 |
from datasets import load_dataset
|
7 |
|
8 |
-
ai4code_ds = load_dataset("CarperAI/pile-v2-small",
|
9 |
-
amps_ds = load_dataset("CarperAI/pile-v2-small",
|
10 |
-
apache_ds = load_dataset("CarperAI/pile-v2-small",
|
11 |
-
books3_ds = load_dataset("CarperAI/pile-v2-small",
|
12 |
-
cp_ds = load_dataset("CarperAI/pile-v2-small",
|
13 |
-
dmmath_ds = load_dataset("CarperAI/pile-v2-small",
|
14 |
-
discourse_ds = load_dataset("CarperAI/pile-v2-small",
|
15 |
-
wiki_ds = load_dataset("CarperAI/pile-v2-small",
|
16 |
-
euro_ds = load_dataset("CarperAI/pile-v2-small",
|
17 |
-
freelaw_ds = load_dataset("CarperAI/pile-v2-small",
|
18 |
-
ghdiffs_ds = load_dataset("CarperAI/pile-v2-small",
|
19 |
-
ghissues_ds = load_dataset("CarperAI/pile-v2-small",
|
20 |
-
gutenberg_ds = load_dataset("CarperAI/pile-v2-small",
|
21 |
-
leet_ds = load_dataset("CarperAI/pile-v2-small",
|
22 |
-
pileoflaw_ds = load_dataset("CarperAI/pile-v2-small",
|
23 |
-
pubmed_ds = load_dataset("CarperAI/pile-v2-small",
|
24 |
-
s2orc_ds = load_dataset("CarperAI/pile-v2-small",
|
25 |
-
se_ds = load_dataset("CarperAI/pile-v2-small",
|
26 |
-
usenet_ds = load_dataset("CarperAI/pile-v2-small",
|
27 |
-
uspto_ds = load_dataset("CarperAI/pile-v2-small",
|
28 |
-
ubuntuirc_ds = load_dataset("CarperAI/pile-v2-small",
|
29 |
-
arxiv_ds = load_dataset("CarperAI/pile-v2-small",
|
30 |
|
31 |
|
32 |
dataset_data = {
|
|
|
5 |
import datasets
|
6 |
from datasets import load_dataset
|
7 |
|
8 |
+
ai4code_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/AI4Code/data.json", use_auth_token=True)
|
9 |
+
amps_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/AMPS/data.json", use_auth_token=True)
|
10 |
+
apache_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/ASFPublicMail/data.json", use_auth_token=True)
|
11 |
+
books3_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/Books3/data.json", use_auth_token=True)
|
12 |
+
cp_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/CPDataset/data.json", use_auth_token=True)
|
13 |
+
dmmath_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/DMMath/data.json", use_auth_token=True)
|
14 |
+
discourse_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/Discourse/data.json", use_auth_token=True)
|
15 |
+
wiki_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/Enwiki/data.json")
|
16 |
+
euro_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/EuroParliamentProceedings/data.json", use_auth_token=True)
|
17 |
+
freelaw_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/FreeLaw_Options/data.json", use_auth_token=True)
|
18 |
+
ghdiffs_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/GitHubDiff/data.json", use_auth_token=True)
|
19 |
+
ghissues_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/GitHubIssues/data.json", use_auth_token=True)
|
20 |
+
gutenberg_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/Gutenberg/data.json", use_auth_token=True)
|
21 |
+
leet_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/LeetCode/data.json", use_auth_token=True)
|
22 |
+
pileoflaw_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/PileOfLaw/data.json", use_auth_token=True)
|
23 |
+
pubmed_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/PubMed/data.json", use_auth_token=True)
|
24 |
+
s2orc_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/S2ORC/data.json", use_auth_token=True)
|
25 |
+
se_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/StackExchange/data.json", use_auth_token=True)
|
26 |
+
usenet_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/USENET/data.json", use_auth_token=True)
|
27 |
+
uspto_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/USPTO/data.json", use_auth_token=True)
|
28 |
+
ubuntuirc_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/UbuntuIRC/data.json", use_auth_token=True)
|
29 |
+
arxiv_ds = load_dataset("CarperAI/pile-v2-small", data_files="data/arXiv/data.json", use_auth_token=True)
|
30 |
|
31 |
|
32 |
dataset_data = {
|