Spaces:
Runtime error
Runtime error
victormiller
commited on
Commit
•
32c6d51
1
Parent(s):
8a3e0e7
Update web.py
Browse files
web.py
CHANGED
@@ -431,11 +431,11 @@ def web_data():
|
|
431 |
"""),
|
432 |
P("We directly read WARC files instead of WET files and extracted text using Trafilatura. Similar to RefinedWeb, we avoid using Machine Learning (ML)-based metrics for filtering documents to prevent bias introduced by ML models. Importantly, we apply global deduplication across the entire dataset, whereas previous works only use local deduplication. Note that although The Pile also employed global deduplication on its web data (Pile-CC), this accounted for just 0.6\% of 74 snapshots."),
|
433 |
|
434 |
-
|
435 |
-
|
436 |
-
|
437 |
-
|
438 |
-
DV2("data/sample_wet.json", "data/sample_warc.json", 3),
|
439 |
|
440 |
H4("1.2 Language Identification"),
|
441 |
P("""
|
@@ -443,7 +443,7 @@ def web_data():
|
|
443 |
This step removes over 60% of the whole data.
|
444 |
"""),
|
445 |
|
446 |
-
|
447 |
Summary("Sample documents that are classified as non-English"),
|
448 |
DV("data/sample_non_en.json", 3),
|
449 |
),
|
|
|
431 |
"""),
|
432 |
P("We directly read WARC files instead of WET files and extracted text using Trafilatura. Similar to RefinedWeb, we avoid using Machine Learning (ML)-based metrics for filtering documents to prevent bias introduced by ML models. Importantly, we apply global deduplication across the entire dataset, whereas previous works only use local deduplication. Note that although The Pile also employed global deduplication on its web data (Pile-CC), this accounted for just 0.6\% of 74 snapshots."),
|
433 |
|
434 |
+
# Details(
|
435 |
+
# Summary("Text Extraction Examples"),
|
436 |
+
# DV2("data/sample_wet.json", "data/sample_warc.json", 3),
|
437 |
+
# ),
|
438 |
+
#DV2("data/sample_wet.json", "data/sample_warc.json", 3),
|
439 |
|
440 |
H4("1.2 Language Identification"),
|
441 |
P("""
|
|
|
443 |
This step removes over 60% of the whole data.
|
444 |
"""),
|
445 |
|
446 |
+
Details(
|
447 |
Summary("Sample documents that are classified as non-English"),
|
448 |
DV("data/sample_non_en.json", 3),
|
449 |
),
|