zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-06-24 17:31:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix detokenizer space match for quote (#1072)

Browse Source 
* fix + test

* remove transformer flax/torch warning

* format
This commit is contained in:
Awni Hannun 2024-10-27 15:06:07 -07:00 committed by GitHub
parent ab4bf05c6e
commit 8fe9539af7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llms/mlx_lm/__init__.py
View File

@ -1,4 +1,9 @@
# Copyright © 2023-2024 Apple Inc. # Copyright © 2023-2024 Apple Inc.
import os
from ._version import __version__ from ._version import __version__
os.environ["TRANSFORMERS_NO_ADVISORY_WARNINGS"] = "1"
from .utils import convert, generate, load, stream_generate from .utils import convert, generate, load, stream_generate

2
llms/mlx_lm/tokenizer_utils.py
View File

@ -169,7 +169,7 @@ class BPEStreamingDetokenizer(StreamingDetokenizer):
""" """
_byte_decoder = None _byte_decoder = None
_space_matches = (".", "?", "!", ",", "'", "n't", "'m", "'s", "'ve", "'re") _space_matches = (".", "?", "!", ",", "n't", "'m", "'s", "'ve", "'re")
def __init__(self, tokenizer): def __init__(self, tokenizer):

3
llms/tests/test_tokenizers.py
View File

@ -51,6 +51,9 @@ class TestTokenizers(unittest.TestCase):
tokens = tokenizer.encode("3 3") tokens = tokenizer.encode("3 3")
check(tokens) check(tokens)
tokens = tokenizer.encode("import 'package:flutter/material.dart';")
check(tokens)
def test_tokenizers(self): def test_tokenizers(self):
tokenizer_repos = [ tokenizer_repos = [
("mlx-community/Qwen1.5-0.5B-Chat-4bit", BPEStreamingDetokenizer), ("mlx-community/Qwen1.5-0.5B-Chat-4bit", BPEStreamingDetokenizer),