Add code-prose tagger to init import.

Additionally update commentary and word choice.
allenai · Feb 28, 2025 · e715591 · e715591
1 parent db8b744
commit e715591
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 4 deletions.
diff --git a/python/dolma/taggers/__init__.py b/python/dolma/taggers/__init__.py
@@ -1,6 +1,7 @@
 from . import (
     c4,
     code,
+    code_composition,
     gopher,
     jigsaw,
     language,

diff --git a/tests/python/conftest.py b/tests/python/conftest.py
@@ -4,11 +4,11 @@
 
 
 # The default multiprocessing start method is "fork" which is not compatible with
-# with runtime assertions that it is set to spawn. When running unit tests, it's
-# possible to call an external library that sets the start method to "fork".
-# Here we enforce the start method to be "spawn" for all tests before executing.
+# with runtime assertions that it is set to "spawn". When running unit tests, it's
+# possible to call an external library that sets the start method to the default.
+# Here we set the start method to be "spawn" for all tests before executing.
 @pytest.fixture(scope="session", autouse=True)
-def initialize_data_environment():
+def initialize_multiprocessing_start_method():
     try:
         multiprocessing.set_start_method("spawn")
     except Exception: