zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-06-24 09:21:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix (#1079)

Browse Source
This commit is contained in:
Awni Hannun 2024-11-01 16:30:32 -07:00 committed by GitHub
parent e510987870
commit 0f799947d0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llms/mlx_lm/tokenizer_utils.py
View File

@ -186,6 +186,8 @@ class BPEStreamingDetokenizer(StreamingDetokenizer):
# https://github.com/openai/gpt-2/blob/master/src/encoder.py
self.make_byte_decoder()
self._added_ids = set(tokenizer.added_tokens_decoder.keys())
def reset(self):
self.offset = 0
self._unflushed = ""
@ -205,11 +207,16 @@ class BPEStreamingDetokenizer(StreamingDetokenizer):
def add_token(self, token):
v = self.tokenmap[token]
if self._byte_decoder[v[0]] == 32:
is_added = token in self._added_ids
if is_added or self._byte_decoder[v[0]] == 32:
current_text = bytearray(
self._byte_decoder[c] for c in self._unflushed
).decode("utf-8")
self.text += self._maybe_trim_space(current_text)
if is_added:
self.text += v
self._unflushed = ""
else:
self._unflushed = v
else:
self._unflushed += v

11
llms/tests/test_tokenizers.py
View File

@ -74,6 +74,17 @@ class TestTokenizers(unittest.TestCase):
tokenizer._detokenizer = NaiveStreamingDetokenizer(tokenizer)
self.check_tokenizer(tokenizer)
def test_special_tokens(self):
tokenizer_repo = "mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx"
tokenizer = self.download_tokenizer(tokenizer_repo)
detokenizer = tokenizer.detokenizer
detokenizer.reset()
detokenizer.add_token(tokenizer.eos_token_id)
detokenizer.finalize()
self.assertEqual(detokenizer.last_segment, tokenizer.eos_token)
if __name__ == "__main__":
unittest.main()