bahasallamatokenizer.py

# coding=utf-8
# Copyright 2020 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from shutil import copyfile
from typing import Optional, Tuple, Union, List
import re
import codecs

from tokenizers import processors

from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
from transformers.utils import is_sentencepiece_available, logging
from transformers.utils.versions import require_version


require_version("tokenizers>=0.13.3")

if is_sentencepiece_available():
    from transformers.models.llama.tokenization_llama import LlamaTokenizer
else:
    LlamaTokenizer = None

logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model", "tokenizer_file": "tokenizer.json"}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer.model",
    },
    "tokenizer_file": {
        "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer_config.json",
    },
}
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"

# fmt: off
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."""
# fmt: on


class LlamaTokenizerFast(PreTrainedTokenizerFast):
    """
    Construct a Llama tokenizer. Based on byte-level Byte-Pair-Encoding.

    This uses notably ByteFallback and no normalization.

    ```python
    >>> from transformers import LlamaTokenizerFast

    >>> tokenizer = LlamaTokenizerFast.from_pretrained("hf-internal-testing/llama-tokenizer")
    >>> tokenizer.encode("Hello this is a test")
    [1, 15043, 445, 338, 263, 1243]
    ```

    If you want to change the `bos_token` or the `eos_token`, make sure to specify them when initializing the model, or
    call `tokenizer.update_post_processor()` to make sure that the post-processing is correctly done (otherwise the
    values of the first token and final token of an encoded sequence will not be correct). For more details, checkout
    [post-processors] (https://huggingface.co/docs/tokenizers/api/post-processors) documentation.


    This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
    refer to this superclass for more information regarding those methods.

    Args:
        vocab_file (`str`, *optional*):
            [SentencePiece](https://github.com/google/sentencepiece) file (generally has a .model extension) that
            contains the vocabulary necessary to instantiate a tokenizer.
        tokenizer_file (`str`, *optional*):
            [tokenizers](https://github.com/huggingface/tokenizers) file (generally has a .json extension) that
            contains everything needed to load the tokenizer.
        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
            Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
            extra spaces.
        unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<unk>"`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<s>"`):
            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
        eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"</s>"`):
            The end of sequence token.
        add_bos_token (`bool`, *optional*, defaults to `True`):
            Whether or not to add an `bos_token` at the start of sequences.
        add_eos_token (`bool`, *optional*, defaults to `False`):
            Whether or not to add an `eos_token` at the end of sequences.
        use_default_system_prompt (`bool`, *optional*, defaults to `False`):
            Whether or not the default system prompt for Llama should be used.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    slow_tokenizer_class = LlamaTokenizer
    padding_side = "left"
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file=None,
        tokenizer_file=None,
        clean_up_tokenization_spaces=False,
        unk_token="<unk>",
        bos_token="<s>",
        eos_token="</s>",
        add_bos_token=True,
        add_eos_token=False,
        use_default_system_prompt=False,
        **kwargs,
    ):
        super().__init__(
            vocab_file=vocab_file,
            tokenizer_file=tokenizer_file,
            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
            unk_token=unk_token,
            bos_token=bos_token,
            eos_token=eos_token,
            add_bos_token=add_bos_token,
            add_eos_token=add_eos_token,
            use_default_system_prompt=use_default_system_prompt,
            **kwargs,
        )
        self._add_bos_token = add_bos_token
        self._add_eos_token = add_eos_token
        self.update_post_processor()
        self.use_default_system_prompt = use_default_system_prompt
        self.vocab_file = vocab_file

    @property
    def can_save_slow_tokenizer(self) -> bool:
        return os.path.isfile(self.vocab_file) if self.vocab_file else False

    def update_post_processor(self):
        """
        Updates the underlying post processor with the current `bos_token` and `eos_token`.
        """
        bos = self.bos_token
        bos_token_id = self.bos_token_id
        if bos is None and self.add_bos_token:
            raise ValueError("add_bos_token = True but bos_token = None")

        eos = self.eos_token
        eos_token_id = self.eos_token_id
        if eos is None and self.add_eos_token:
            raise ValueError("add_eos_token = True but eos_token = None")

        single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
        pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"

        special_tokens = []
        if self.add_bos_token:
            special_tokens.append((bos, bos_token_id))
        if self.add_eos_token:
            special_tokens.append((eos, eos_token_id))
        self._tokenizer.post_processor = processors.TemplateProcessing(
            single=single, pair=pair, special_tokens=special_tokens
        )

    @property
    def add_eos_token(self):
        return self._add_eos_token

    @property
    def add_bos_token(self):
        return self._add_bos_token

    @add_eos_token.setter
    def add_eos_token(self, value):
        self._add_eos_token = value
        self.update_post_processor()

    @add_bos_token.setter
    def add_bos_token(self, value):
        self._add_bos_token = value
        self.update_post_processor()

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        if not self.can_save_slow_tokenizer:
            raise ValueError(
                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
                "tokenizer."
            )

        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):
            copyfile(self.vocab_file, out_vocab_file)

        return (out_vocab_file,)

    @property
    # Copied from transformers.models.llama.tokenization_llama.LlamaTokenizer.default_chat_template
    def default_chat_template(self):
        """
        LLaMA uses [INST] and [/INST] to indicate user messages, and <<SYS>> and <</SYS>> to indicate system messages.
        Assistant messages do not have special tokens, because LLaMA chat models are generally trained with strict
        user/assistant/user/assistant message ordering, and so assistant messages can be identified from the ordering
        rather than needing special tokens. The system message is partly 'embedded' in the first user message, which
        results in an unusual token ordering when it is present. This template should definitely be changed if you wish
        to fine-tune a model with more flexible role ordering!

        The output should look something like:

        <bos>[INST] B_SYS SystemPrompt E_SYS Prompt [/INST] Answer <eos><bos>[INST] Prompt [/INST] Answer <eos>
        <bos>[INST] Prompt [/INST]

        The reference for this chat template is [this code
        snippet](https://github.com/facebookresearch/llama/blob/556949fdfb72da27c2f4a40b7f0e4cf0b8153a28/llama/generation.py#L320-L362)
        in the original repository.
        """
        logger.warning_once(
            "\nNo chat template is defined for this tokenizer - using the default template "
            f"for the {self.__class__.__name__} class. If the default is not appropriate for "
            "your model, please set `tokenizer.chat_template` to an appropriate template. "
            "See https://huggingface.co/docs/transformers/main/chat_templating for more information.\n"
        )
        template = (
            "{% if messages[0]['role'] == 'system' %}"
            "{% set loop_messages = messages[1:] %}"  # Extract system message if it's present
            "{% set system_message = messages[0]['content'] %}"
            "{% elif USE_DEFAULT_PROMPT == true and not '<<SYS>>' in messages[0]['content'] %}"
            "{% set loop_messages = messages %}"  # Or use the default system message if the flag is set
            "{% set system_message = 'DEFAULT_SYSTEM_MESSAGE' %}"
            "{% else %}"
            "{% set loop_messages = messages %}"
            "{% set system_message = false %}"
            "{% endif %}"
            "{% for message in loop_messages %}"  # Loop over all non-system messages
            "{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}"
            "{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}"
            "{% endif %}"
            "{% if loop.index0 == 0 and system_message != false %}"  # Embed system message in first message
            "{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}"
            "{% else %}"
            "{% set content = message['content'] %}"
            "{% endif %}"
            "{% if message['role'] == 'user' %}"  # After all of that, handle messages/roles in a fairly normal way
            "{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}"
            "{% elif message['role'] == 'system' %}"
            "{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}"
            "{% elif message['role'] == 'assistant' %}"
            "{{ ' '  + content.strip() + ' ' + eos_token }}"
            "{% endif %}"
            "{% endfor %}"
        )
        template = template.replace("USE_DEFAULT_PROMPT", "true" if self.use_default_system_prompt else "false")
        default_message = DEFAULT_SYSTEM_PROMPT.replace("\n", "\\n").replace("'", "\\'")
        template = template.replace("DEFAULT_SYSTEM_MESSAGE", default_message)

        return template

    # TODO ArthurZ let's rely on the template processor instead, refactor all fast tokenizers
    # Copied from transformers.models.llama.tokenization_llama.LlamaTokenizer.build_inputs_with_special_tokens
    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 decode_hex_in_sentence(self,sentence):
            # Define a regular expression to match hexadecimal representations
            hex_pattern = re.compile(r'<0x([0-9A-Fa-f]+)>')

            # Find all matches in the sentence
            matches = re.finditer(hex_pattern, sentence)

            # Iterate over matches and replace them with their decoded values
            for match in matches:
                hex_string = match.group(1)
                bytes_data = bytes.fromhex(hex_string)
                try:
                    decoded_string = bytes_data.decode('utf-8')
                except UnicodeDecodeError:
                    continue
                sentence = sentence.replace(match.group(0), decoded_string, 1)

            return sentence
        
    def convert_emojis(self,input_string):
        # Find all hexadecimal escape sequences in the input string
        hex_sequences = re.findall(r'<0x([A-Fa-f0-9]+)>', input_string)

        input_string = bytes(input_string,'utf-8')
    
        # Replace each escape sequence with its decoded equivalent
        for hex_seq in hex_sequences:
            bytes_value = bytes.fromhex(hex_seq)
            input_string = input_string.replace(bytes(f"<0x{hex_seq}>",'utf-8'), bytes_value)

        decoded_str = codecs.decode(input_string, 'utf-8')

        return decoded_str

    def _decode(
        self,
        token_ids: Union[int, List[int]],
        skip_special_tokens: bool = False,
        clean_up_tokenization_spaces: bool = None,
        **kwargs,
    ) -> str:

        self._decode_use_source_tokenizer = kwargs.pop("use_source_tokenizer", False)

        if isinstance(token_ids, int):
            token_ids = [token_ids]

        # custom logic since there's some spacing issue with AddedToken 
        tokens = self.convert_ids_to_tokens(token_ids)
        text = ""
        i = 0
        for id,token in zip(token_ids,tokens):
            if skip_special_tokens and id in self.all_special_ids:
                continue

            if id>=32000 and i!= 0: #check for AddedToken and not the first token
                text += " " + token
            else:
                text += token
            i += 1
        text = re.sub("▁"," ",text)
        text = self.decode_hex_in_sentence(text)
        text = self.convert_emojis(text)
        text = text.lstrip().rstrip()

        clean_up_tokenization_spaces = (
            clean_up_tokenization_spaces
            if clean_up_tokenization_spaces is not None
            else self.clean_up_tokenization_spaces
        )
        if clean_up_tokenization_spaces:
            clean_text = self.clean_up_tokenization(text)
            return clean_text
        else:
            return text