|
|
|
|
|
|
|
"""Tokenization classes for Skywork.""" |
|
import os |
|
from shutil import copyfile |
|
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple |
|
|
|
import sentencepiece as spm |
|
|
|
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer |
|
from transformers.utils import logging |
|
|
|
if TYPE_CHECKING: |
|
from transformers.pipelines.conversational import Conversation |
|
|
|
logger = logging.get_logger(__name__) |
|
|
|
VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} |
|
|
|
|
|
SPIECE_UNDERLINE = "▁" |
|
|
|
B_INST, E_INST = "[INST]", "[/INST]" |
|
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n" |
|
|
|
DEFAULT_SYSTEM_PROMPT = """You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure\ |
|
that your responses are socially unbiased and positive in nature. |
|
|
|
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""" |
|
|
|
class SkyworkTokenizer(PreTrainedTokenizer): |
|
|
|
vocab_files_names = VOCAB_FILES_NAMES |
|
|
|
|
|
model_input_names = ["input_ids", "attention_mask"] |
|
|
|
def __init__( |
|
self, |
|
vocab_file, |
|
unk_token="<unk>", |
|
bos_token="<s>", |
|
eos_token="</s>", |
|
pad_token=None, |
|
sp_model_kwargs: Optional[Dict[str, Any]] = None, |
|
add_bos_token=True, |
|
add_eos_token=False, |
|
clean_up_tokenization_spaces=False, |
|
legacy=True, |
|
**kwargs, |
|
): |
|
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs |
|
bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token |
|
eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token |
|
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token |
|
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token |
|
self.legacy = legacy |
|
self.vocab_file = vocab_file |
|
self.add_bos_token = add_bos_token |
|
self.add_eos_token = add_eos_token |
|
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) |
|
self.sp_model.Load(vocab_file) |
|
super().__init__( |
|
bos_token=bos_token, |
|
eos_token=eos_token, |
|
unk_token=unk_token, |
|
pad_token=pad_token, |
|
add_bos_token=add_bos_token, |
|
add_eos_token=add_eos_token, |
|
sp_model_kwargs=self.sp_model_kwargs, |
|
clean_up_tokenization_spaces=clean_up_tokenization_spaces, |
|
legacy=legacy, |
|
**kwargs, |
|
) |
|
if legacy: |
|
logger.warning_once( |
|
f"You are using the legacy behaviour of the {self.__class__}. This means that tokens that come after special tokens will not be properly handled. " |
|
) |
|
|
|
|
|
def __getstate__(self): |
|
state = self.__dict__.copy() |
|
state["sp_model"] = None |
|
state["sp_model_proto"] = self.sp_model.serialized_model_proto() |
|
return state |
|
|
|
def __setstate__(self, d): |
|
self.__dict__ = d |
|
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs) |
|
self.sp_model.LoadFromSerializedProto(self.sp_model_proto) |
|
|
|
@property |
|
def vocab_size(self): |
|
"""Returns vocab size""" |
|
return self.sp_model.get_piece_size() |
|
|
|
def get_vocab(self): |
|
"""Returns vocab as a dict""" |
|
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)} |
|
vocab.update(self.added_tokens_encoder) |
|
return vocab |
|
|
|
|
|
def tokenize(self, text, **kwargs) -> List[str]: |
|
|
|
|
|
if not self.legacy: |
|
text = SPIECE_UNDERLINE + text.replace(SPIECE_UNDERLINE, " ") |
|
return super().tokenize(text, **kwargs) |
|
|
|
|
|
def _tokenize(self, text): |
|
if not self.legacy: |
|
is_first = text.startswith(SPIECE_UNDERLINE) |
|
if is_first: |
|
text = text[1:] |
|
|
|
tokens = self.sp_model.encode(text, out_type=str) |
|
|
|
if not self.legacy and not is_first and not text.startswith(" ") and tokens[0].startswith(SPIECE_UNDERLINE): |
|
tokens = ([tokens[0][1:]] if len(tokens[0]) > 1 else []) + tokens[1:] |
|
return tokens |
|
|
|
def _convert_token_to_id(self, token): |
|
"""Converts a token (str) in an id using the vocab.""" |
|
return self.sp_model.piece_to_id(token) |
|
|
|
def _convert_id_to_token(self, index): |
|
"""Converts an index (integer) in a token (str) using the vocab.""" |
|
token = self.sp_model.IdToPiece(index) |
|
return token |
|
|
|
def convert_tokens_to_string(self, tokens): |
|
"""Converts a sequence of tokens (string) in a single string.""" |
|
current_sub_tokens = [] |
|
out_string = "" |
|
prev_is_special = False |
|
for i, token in enumerate(tokens): |
|
|
|
if token in self.all_special_tokens: |
|
if not prev_is_special and i != 0: |
|
out_string += " " |
|
out_string += self.sp_model.decode(current_sub_tokens) + token |
|
prev_is_special = True |
|
current_sub_tokens = [] |
|
else: |
|
current_sub_tokens.append(token) |
|
prev_is_special = False |
|
out_string += self.sp_model.decode(current_sub_tokens) |
|
return out_string |
|
|
|
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]: |
|
if not os.path.isdir(save_directory): |
|
logger.error(f"Vocabulary path ({save_directory}) should be a directory") |
|
return |
|
out_vocab_file = os.path.join( |
|
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"] |
|
) |
|
|
|
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file): |
|
copyfile(self.vocab_file, out_vocab_file) |
|
elif not os.path.isfile(self.vocab_file): |
|
with open(out_vocab_file, "wb") as fi: |
|
content_spiece_model = self.sp_model.serialized_model_proto() |
|
fi.write(content_spiece_model) |
|
|
|
return (out_vocab_file,) |
|
|
|
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None): |
|
bos_token_id = [self.bos_token_id] if self.add_bos_token else [] |
|
eos_token_id = [self.eos_token_id] if self.add_eos_token else [] |
|
|
|
output = bos_token_id + token_ids_0 + eos_token_id |
|
|
|
if token_ids_1 is not None: |
|
output = output + bos_token_id + token_ids_1 + eos_token_id |
|
|
|
return output |
|
|
|
def get_special_tokens_mask( |
|
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False |
|
) -> List[int]: |
|
if already_has_special_tokens: |
|
return super().get_special_tokens_mask( |
|
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True |
|
) |
|
|
|
bos_token_id = [1] if self.add_bos_token else [] |
|
eos_token_id = [1] if self.add_eos_token else [] |
|
|
|
if token_ids_1 is None: |
|
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id |
|
return ( |
|
bos_token_id |
|
+ ([0] * len(token_ids_0)) |
|
+ eos_token_id |
|
+ bos_token_id |
|
+ ([0] * len(token_ids_1)) |
|
+ eos_token_id |
|
) |
|
|
|
def create_token_type_ids_from_sequences( |
|
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None |
|
) -> List[int]: |
|
bos_token_id = [self.bos_token_id] if self.add_bos_token else [] |
|
eos_token_id = [self.eos_token_id] if self.add_eos_token else [] |
|
|
|
output = [0] * len(bos_token_id + token_ids_0 + eos_token_id) |
|
|
|
if token_ids_1 is not None: |
|
output += [1] * len(bos_token_id + token_ids_1 + eos_token_id) |
|
|
|
return output |
|
|
|
def _build_conversation_input_ids(self, conversation: "Conversation") -> List[int]: |
|
dialogue = list(conversation.iter_texts()) |
|
if not all([is_user for is_user, msg in dialogue[::2]]) or not all( |
|
[not is_user for is_user, msg in dialogue[1::2]] |
|
): |
|
raise ValueError( |
|
"The model only supports 'user' and 'assistant' roles, starting with user and alternating (u/a/u/a/u...)" |
|
) |
|
|
|
dialog_tokens: List[int] = [] |
|
if len(conversation.past_user_inputs) > 0: |
|
if not conversation.past_user_inputs[0].startswith(B_SYS) or E_SYS not in conversation.past_user_inputs[0]: |
|
conversation.past_user_inputs[0] = ( |
|
B_SYS + DEFAULT_SYSTEM_PROMPT + E_SYS + conversation.past_user_inputs[0] |
|
) |
|
elif not dialogue[0][1].startswith(B_SYS) or E_SYS not in dialogue[0][1]: |
|
dialogue[0] = (dialogue[0][0], B_SYS + DEFAULT_SYSTEM_PROMPT + E_SYS + dialogue[0][1]) |
|
|
|
dialog_tokens += sum( |
|
[ |
|
[self.bos_token_id] |
|
+ self.encode( |
|
f"{B_INST} {(prompt[1]).strip()} {E_INST} {(answer[1]).strip()} ", add_special_tokens=False |
|
) |
|
+ [self.eos_token_id] |
|
for prompt, answer in zip(dialogue[::2], dialogue[1::2]) |
|
], |
|
[], |
|
) |
|
if not (dialogue[-1][0]): |
|
raise ValueError(f"Last message must be from user, got {dialogue[-1]['role']}") |
|
dialog_tokens += [self.bos_token_id] + self.encode( |
|
f"{B_INST} {(dialogue[-1][1]).strip()} {E_INST}", add_special_tokens=False |
|
) |
|
return dialog_tokens |
|
|
