Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Harry Mellor <hej.mellor@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
804e5377aa
commit
8c1557a79c
@@ -13,9 +13,7 @@ from .protocol import TokenizerLike
|
||||
|
||||
|
||||
def get_deepseek_v32_tokenizer(tokenizer: HfTokenizer) -> HfTokenizer:
|
||||
"""
|
||||
Wraps a tokenizer to use the custom DeepSeek V3.2 chat template encoding.
|
||||
"""
|
||||
"""Wraps a tokenizer to use the custom DeepSeek V3.2 chat template encoding."""
|
||||
dsv32_tokenizer = copy.copy(tokenizer)
|
||||
|
||||
added_vocab = tokenizer.get_added_vocab()
|
||||
|
||||
@@ -13,9 +13,7 @@ from .protocol import TokenizerLike
|
||||
|
||||
|
||||
def get_deepseek_v4_tokenizer(tokenizer: HfTokenizer) -> HfTokenizer:
|
||||
"""
|
||||
Wraps a tokenizer to use the custom DeepSeek V4 chat template encoding.
|
||||
"""
|
||||
"""Wraps a tokenizer to use the custom DeepSeek V4 chat template encoding."""
|
||||
dsv4_tokenizer = copy.copy(tokenizer)
|
||||
|
||||
added_vocab = tokenizer.get_added_vocab()
|
||||
|
||||
@@ -205,6 +205,7 @@ def detokenize_incrementally(
|
||||
skip_special_tokens: Whether to skip special tokens.
|
||||
spaces_between_special_tokens: Whether to add spaces between special
|
||||
tokens.
|
||||
|
||||
"""
|
||||
new_token_id = all_input_ids[-1]
|
||||
# This is the first iteration for this sequence
|
||||
|
||||
@@ -23,8 +23,7 @@ class ThreadSafeHFTokenizerMixin:
|
||||
|
||||
|
||||
def maybe_make_thread_pool(tokenizer: _T, copies: int = 1):
|
||||
"""
|
||||
If `tokenizer` is a `TokenizersBackend`, modify the tokenizer
|
||||
"""If `tokenizer` is a `TokenizersBackend`, modify the tokenizer
|
||||
in-place to make the public interface thread-safe by routing calls
|
||||
through a deep-copied tokenizer pool.
|
||||
|
||||
@@ -105,8 +104,7 @@ def maybe_make_thread_pool(tokenizer: _T, copies: int = 1):
|
||||
|
||||
|
||||
def get_cached_tokenizer(tokenizer: HfTokenizer) -> HfTokenizer:
|
||||
"""
|
||||
By default, transformers will recompute multiple tokenizer properties
|
||||
"""By default, transformers will recompute multiple tokenizer properties
|
||||
each time they are called, leading to a significant slowdown.
|
||||
This proxy caches these properties for faster access.
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user