dnrops
/
transformers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update to tokenizers version

This commit is contained in:
Arthur Zucker 2024-04-02 10:45:27 +02:00
parent 416711c3ea
commit ca5d48983b
3 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@ -174,7 +174,7 @@ _deps = [
"tf2onnx",
"timeout-decorator",
"timm",
"tokenizers>=0.14,<0.19",
"tokenizers>=0.16,<0.19",
"torch",
"torchaudio",
"torchvision",

11
src/transformers/convert_slow_tokenizer.py
View File

@ -601,14 +601,15 @@ class SpmConverter(Converter):
if hasattr(self.original_tokenizer, "legacy") and not self.original_tokenizer.legacy:
prepend_scheme = "first"
return pre_tokenizers.Metaspace(
replacement=replacement, add_prefix_space=add_prefix_space, prepend_scheme=prepend_scheme
replacement=replacement, prepend_scheme=prepend_scheme
)
def post_processor(self):
return None
def decoder(self, replacement, add_prefix_space):
return decoders.Metaspace(replacement=replacement, add_prefix_space=add_prefix_space)
prepend_scheme = "always" if add_prefix_space else "never"
return decoders.Metaspace(replacement=replacement, prepend_scheme=prepend_scheme)
def converted(self) -> Tokenizer:
tokenizer = self.tokenizer(self.proto)
@ -722,7 +723,8 @@ class DebertaV2Converter(SpmConverter):
list_pretokenizers = []
if self.original_tokenizer.split_by_punct:
list_pretokenizers.append(pre_tokenizers.Punctuation(behavior="isolated"))
list_pretokenizers.append(pre_tokenizers.Metaspace(replacement=replacement, add_prefix_space=add_prefix_space))
prepend_scheme = "always" if add_prefix_space else "never"
list_pretokenizers.append(pre_tokenizers.Metaspace(replacement=replacement, prepend_scheme=prepend_scheme))
return pre_tokenizers.Sequence(list_pretokenizers)
def normalizer(self, proto):
@ -1007,10 +1009,11 @@ class PegasusConverter(SpmConverter):
return proto.trainer_spec.unk_id + self.original_tokenizer.offset
def pre_tokenizer(self, replacement, add_prefix_space):
prepend_scheme = "always" if add_prefix_space else "never"
return pre_tokenizers.Sequence(
[
pre_tokenizers.WhitespaceSplit(),
pre_tokenizers.Metaspace(replacement=replacement, add_prefix_space=add_prefix_space),
pre_tokenizers.Metaspace(replacement=replacement, prepend_scheme=prepend_scheme),
]
)

2
src/transformers/dependency_versions_table.py
View File

@ -79,7 +79,7 @@ deps = {
"tf2onnx": "tf2onnx",
"timeout-decorator": "timeout-decorator",
"timm": "timm",
"tokenizers": "tokenizers>=0.14,<0.19",
"tokenizers": "tokenizers>=0.16,<0.19",
"torch": "torch",
"torchaudio": "torchaudio",
"torchvision": "torchvision",