mirror of
https://github.com/gentoo-mirror/gentoo.git
synced 2025-12-21 21:17:37 -08:00
40 lines
1.7 KiB
Diff
40 lines
1.7 KiB
Diff
--- a/tests/bindings/test_trainers.py 2024-04-07 18:21:19.443506351 +0200
|
|
+++ b/tests/bindings/test_trainers.py 2024-04-07 18:21:54.893466083 +0200
|
|
@@ -295,8 +295,8 @@
|
|
tokenizer.pre_tokenizer = pre_tokenizers.Sequence(
|
|
[pre_tokenizers.Whitespace(), pre_tokenizers.Digits(individual_digits=True)]
|
|
)
|
|
- tokenizer.train(files=["data/big.txt"], trainer=trainer)
|
|
+ tokenizer.train(files=["tests/data/big.txt"], trainer=trainer)
|
|
|
|
- tokenizer.save("data/tokenizer.json")
|
|
+ tokenizer.save("tests/data/tokenizer.json")
|
|
|
|
- tokenizer.from_file("data/tokenizer.json")
|
|
+ tokenizer.from_file("tests/data/tokenizer.json")
|
|
--- a/tests/documentation/test_tutorial_train_from_iterators.py 2024-04-07 18:19:08.653593406 +0200
|
|
+++ b/tests/documentation/test_tutorial_train_from_iterators.py 2024-04-07 18:19:39.206906910 +0200
|
|
@@ -40,7 +40,7 @@
|
|
def setup_gzip_files(self, train_files):
|
|
with open(train_files["small"], "rt") as small:
|
|
for n in range(3):
|
|
- path = f"data/my-file.{n}.gz"
|
|
+ path = f"tests/data/my-file.{n}.gz"
|
|
with gzip.open(path, "wt") as f:
|
|
f.write(small.read())
|
|
|
|
@@ -87,11 +87,11 @@
|
|
# START single_gzip
|
|
import gzip
|
|
|
|
- with gzip.open("data/my-file.0.gz", "rt") as f:
|
|
+ with gzip.open("tests/data/my-file.0.gz", "rt") as f:
|
|
tokenizer.train_from_iterator(f, trainer=trainer)
|
|
# END single_gzip
|
|
# START multi_gzip
|
|
- files = ["data/my-file.0.gz", "data/my-file.1.gz", "data/my-file.2.gz"]
|
|
+ files = ["tests/data/my-file.0.gz", "tests/data/my-file.1.gz", "tests/data/my-file.2.gz"]
|
|
|
|
def gzip_iterator():
|
|
for path in files:
|