[CI] Fix mypy for vllm/reasoning (#35742)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
co-authored by
Harry Mellor
parent
5282c7d4d0
commit
7f1f36bf91
@@ -4,7 +4,7 @@
|
||||
|
||||
import functools
|
||||
import json
|
||||
from collections.abc import Collection, Set
|
||||
from collections.abc import Collection, Sequence, Set
|
||||
from pathlib import Path
|
||||
from typing import Any, Literal, overload
|
||||
|
||||
@@ -348,7 +348,9 @@ class Grok2Tokenizer(TokenizerLike):
|
||||
tokens = self._maybe_truncate(tokens, max_length)
|
||||
return tokens
|
||||
|
||||
def decode(self, ids: list[int] | int, skip_special_tokens: bool = False) -> str:
|
||||
def decode(
|
||||
self, ids: Sequence[int] | int, skip_special_tokens: bool = False
|
||||
) -> str:
|
||||
if isinstance(ids, int):
|
||||
ids = [ids]
|
||||
if skip_special_tokens:
|
||||
@@ -371,7 +373,7 @@ class Grok2Tokenizer(TokenizerLike):
|
||||
return [self._token_to_id.get(token, self._unk_token_id) for token in tokens]
|
||||
|
||||
def convert_ids_to_tokens(
|
||||
self, ids: list[int], skip_special_tokens: bool = False
|
||||
self, ids: Sequence[int], skip_special_tokens: bool = False
|
||||
) -> list[str]:
|
||||
tokens = []
|
||||
for token_id in ids:
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
from collections.abc import Sequence
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, cast, overload
|
||||
|
||||
@@ -434,7 +435,9 @@ class MistralTokenizer(TokenizerLike):
|
||||
return_dict=False,
|
||||
)
|
||||
|
||||
def decode(self, ids: list[int] | int, skip_special_tokens: bool = False) -> str:
|
||||
def decode(
|
||||
self, ids: Sequence[int] | int, skip_special_tokens: bool = False
|
||||
) -> str:
|
||||
# TODO(juliendenize): once https://github.com/huggingface/transformers/pull/41962
|
||||
# is in, directly call self.transformers_tokenizer.decode(...).
|
||||
if isinstance(ids, int):
|
||||
@@ -512,7 +515,7 @@ class MistralTokenizer(TokenizerLike):
|
||||
|
||||
def convert_ids_to_tokens(
|
||||
self,
|
||||
ids: list[int],
|
||||
ids: Sequence[int],
|
||||
skip_special_tokens: bool = False,
|
||||
) -> list[str]:
|
||||
if not skip_special_tokens:
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
from collections.abc import Sequence
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, Protocol, overload
|
||||
|
||||
@@ -116,12 +117,14 @@ class TokenizerLike(Protocol):
|
||||
def convert_tokens_to_string(self, tokens: list[str]) -> str:
|
||||
raise NotImplementedError
|
||||
|
||||
def decode(self, ids: list[int] | int, skip_special_tokens: bool = False) -> str:
|
||||
def decode(
|
||||
self, ids: Sequence[int] | int, skip_special_tokens: bool = False
|
||||
) -> str:
|
||||
raise NotImplementedError
|
||||
|
||||
def convert_ids_to_tokens(
|
||||
self,
|
||||
ids: list[int],
|
||||
ids: Sequence[int],
|
||||
skip_special_tokens: bool = False,
|
||||
) -> list[str]:
|
||||
raise NotImplementedError
|
||||
|
||||
Reference in New Issue
Block a user