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

Jump to bottom

Fix generation of multi-token unicode characters #738

Merged
merged 2 commits into from
Mar 14, 2024
Merged

Fix generation of multi-token unicode characters #738

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
c406299
Add a function to convert utf8 regexps into regexps that operates ove…
ksvladimir Mar 11, 2024
8922151
Support generating multi-byte utf8 characters
ksvladimir Mar 11, 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
14 changes: 11 additions & 3 deletions outlines/fsm/guide.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,11 @@

from outlines import grammars
from outlines.caching import cache
from outlines.fsm.regex import create_fsm_index_tokenizer, make_deterministic_fsm
from outlines.fsm.regex import (
create_fsm_index_tokenizer,
make_byte_level_fsm,
make_deterministic_fsm,
)

if TYPE_CHECKING:
from outlines.models.tokenizer import Tokenizer
Expand Down Expand Up @@ -111,7 +115,10 @@ def create_states_mapping(
The parameters of the function are used for caching purpose
"""
regex_pattern = interegular.parse_pattern(regex_string)
regex_fsm, _ = make_deterministic_fsm(regex_pattern.to_fsm().reduce())
byte_fsm = make_byte_level_fsm(
regex_pattern.to_fsm().reduce(), keep_utf8=True
)
regex_fsm, _ = make_deterministic_fsm(byte_fsm)
states_to_token_maps, empty_token_ids = create_fsm_index_tokenizer(
regex_fsm, tokenizer
)
Expand Down Expand Up @@ -211,7 +218,8 @@ def create_states_mapping_from_interegular_fsm(
"""Create the variables related to the mapping between states and tokens
The parameters of the function are used for caching purpose
"""
regex_fsm, _ = make_deterministic_fsm(fsm.reduce())
byte_fsm = make_byte_level_fsm(fsm.reduce(), keep_utf8=True)
regex_fsm, _ = make_deterministic_fsm(byte_fsm)
states_to_token_maps, empty_token_ids = create_fsm_index_tokenizer(
regex_fsm, tokenizer
)
Expand Down
Loading
Loading