Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Allow multiple response patterns in the insert_mask_before_placeholder transform #2567

Merged
merged 2 commits into from
Mar 13, 2024
Merged

Allow multiple response patterns in the insert_mask_before_placeholder transform #2567

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3dca0df
updated onmt/transforms/insert_mask_before_placeholder.py"
l-k-11235 Mar 12, 2024
eacda99
updated onmt/tests/test_transform.py
l-k-11235 Mar 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion onmt/tests/test_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -788,7 +788,7 @@ class TestInsertMaskBeforePlaceholder(unittest.TestCase):
@classmethod
def setUpClass(cls):
cls.base_opts = {
"response_pattern": "Response : ｟newline｠",
"response_patterns": ["Response : ｟newline｠"],
}

def test_insert_mask_before_placeholder(self):
Expand Down
26 changes: 15 additions & 11 deletions onmt/transforms/insert_mask_before_placeholder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,24 +22,28 @@ def add_options(cls, parser):
"Transform/InsertMaskBeforePlaceholdersTransform"
)
group.add(
"--response_pattern",
"-response_pattern",
type=str,
"--response_patterns",
"-response_patterns",
help="Response patten to locate the end of the prompt",
default="Response : ｟newline｠",
default=["Response : ｟newline｠"],
nargs="+",
)

def _parse_opts(self):
self.response_pattern = self.opts.response_pattern
self.response_patterns = self.opts.response_patterns

def apply(self, example, is_train=False, stats=None, **kwargs):
_src = " ".join(example["src"])
if len(_src.split(self.response_pattern)) != 2:
response = None
for _pattern in self.response_patterns:
if len(_src.split(_pattern)) == 2:
prompt, response = _src.split(_pattern)
response = DefaultTokens.MASK_BEFORE.join([_pattern, response])
if response is not None:
_src = "".join([prompt, response])
example["src"] = _src.split(" ")
example["tgt"] = _src.split(" ")
else:
logger.info("The mask_before could not be inserted")
return example
prompt, response = _src.split(self.response_pattern)
response = DefaultTokens.MASK_BEFORE.join([self.response_pattern, response])
_src = "".join([prompt, response])
example["src"] = _src.split(" ")
example["tgt"] = _src.split(" ")
return example
Loading