Upload tokenizer

chat_template.jinja

@@ -0,0 +1,112 @@
+{% set loop_messages = messages %}
+{% if tools %}
+    {% set weekday_map = {'Monday': '星期一', 'Tuesday': '星期二', 'Wednesday': '星期三', 'Thursday': '星期四', 'Friday': '星期五', 'Saturday': '星期六', 'Sunday': '星期日'} %}
+    {% set weekday_cn = weekday_map[strftime_now('%A')] %}
+    {% set datetime_str = strftime_now('%Y-%m-%d %H:%M:%S') %}
+    {% set datetime_str = datetime_str + ' ' + weekday_cn %}
+    {% for message in loop_messages %}
+        {% if 'content' in message %}
+            {% set content = message['content'] %}
+        {% else %}
+            {% set content = '' %}
+        {% endif %}
+        {% if loop.index0 == 0 %}
+            {% set content_tmp = '你是一位函数组合专家。你会得到一个问题和一组可能的函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的。
+如果没有一个函数可以使用，请直接使用自然语言回复用户，以助手：开头。
+如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息，以助手：开头。
+如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户，以助手：开头。
+你应该只在工具调用部分返回函数调用。如果你决定调用任何函数，你必须将其格式化为<tool_calls>[{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},...]</tool_calls>。你不应该在回复中包含任何其他文本。以下是你可以调用的函数列表，格式为JSON。
+' %}
+            {% set content_tmp = content_tmp + '
+' + tools | tojson + '
+' %}
+            {% if message['role'] == 'system' %}
+                {% set content_tmp = content_tmp + '
+额外要求：
+' + content + '
+
+如果你决定返回函数调用，请将其格式化为<tool_calls>[{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},...]</tool_calls>，不得包含其他文本。如果额外要求里有格式要求，请忽略，以此处为准。
+否则，请参考开头说的三种情况，以助手：开头进行回复。
+
+如果额外要求里有时间信息，就以额外要求里的时间为准，否则，参考当前时间：' + datetime_str %}
+                {% set content = '<|startoftext|>' + content_tmp + '<|extra_4|>' %}
+            {% elif message['role'] == 'user' %}
+                {% set content_tmp = content_tmp + '
+如果你决定返回函数调用，请将其格式化为<tool_calls>[{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},...]</tool_calls>，不得包含其他文本。
+否则，请参考开头说的三种情况，以助手：开头进行回复。
+
+当前时间：' + datetime_str %}
+                {% set content_tmp = '<|startoftext|>' + content_tmp + '<|extra_4|>'%}
+                {% set content = content_tmp + '用户：' + content + '<|extra_0|>' %}
+            {% endif %}
+        {% else %}
+            {% if message['role'] == 'user' %}
+                {% set content = '用户：' + content + '<|extra_0|>' %}
+            {% elif message['role'] == 'assistant' %}
+                {% if 'tool_calls' in message %}
+                    {% set tool_calls = message['tool_calls'] %}
+                    {% set ns = namespace(tool_calls="[") %}
+                    {% for tool_call in tool_calls %}
+                        {% set function = tool_call['function'] %}
+                        {% set name = function['name'] %}
+                        {% set ns.tool_calls = ns.tool_calls + '{"name": "' + name + '", '%}
+                        {% set arguments = function['arguments'] %}
+                        {% if arguments is not string %}
+                            {% set arguments = arguments | tojson %}
+                        {% endif %}
+                        {% set ns.tool_calls = ns.tool_calls + '"arguments": ' + arguments + '}' %}
+                        {% if not loop.last %}
+                            {% set ns.tool_calls = ns.tool_calls + ', '%}
+                        {% endif %}
+                    {% endfor %}
+                    {% set ns.tool_calls = ns.tool_calls + ']' %}
+                    {% set content = content + '<tool_calls>' + ns.tool_calls + '</tool_calls>' %}
+                {% else %}
+                    {% set content = '助手：' + content %}
+                {% endif %}
+                {% set content = content + '<|eos|>' %}
+            {% elif message['role'] == 'tool' %}
+                {% if content is not string %}
+                    {set content = content | tojson }
+                {% endif %}
+                {% set content = '<tool_response>' + content + '</tool_response>' %}
+                {% set content = content + '<|extra_0|>' %}
+            {% endif %}
+        {% endif %}
+    {{- content -}}
+    {% endfor %}
+{% else %}
+    {% set context = {'has_head': true} %}
+    {% for message in loop_messages %}
+        {% if 'content' in message %}
+            {% set content = message['content'] %}
+        {% else %}
+            {% set content = '' %}
+        {% endif %}
+        {% if loop.index0 == 0 %}
+            {% if content == '' %}
+                {% set _ = context.update({'has_head': false}) %}
+            {% elif message['role'] == 'system' %}
+                {% set content = '<|startoftext|>' + content + '<|extra_4|>' %}
+            {% endif %}
+        {% endif %}
+        {% if message['role'] == 'user' %}
+            {% if loop.index0 == 1 and not context.has_head %}
+                {% set content = '<|startoftext|>' + content %}
+            {% endif %}
+            {% if loop.index0 == 1 and context.has_head %}
+                {% set content = content + '<|extra_0|>' %}
+            {% else %}
+                {% set content = '<|startoftext|>' + content + '<|extra_0|>' %}
+            {% endif %}
+        {% elif message['role'] == 'assistant' %}
+            {% set content = content + '<|eos|>' %}
+        {% elif message['role'] == 'tool' %}
+            {% set content = content + '<|extra_0|>' %}
+        {% endif %}
+        {{- content -}}
+    {% endfor %}
+{% endif %}
+{%- if enable_thinking is defined and enable_thinking is false %}
+    {{- '<think>\n\n</think>\n' }}
+{%- endif %}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|startoftext|>",
+    "<|extra_0|>",
+    "<|extra_4|>",
+    "<|extra_5|>",
+    "<|eos|>"
+  ],
+  "eos_token": "<|eos|>",
+  "pad_token": "<|pad|>"
+}

tokenization_hy.py

@@ -0,0 +1,298 @@
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "hy.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+# PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+STARTOFTEXT = "<|startoftext|>"
+BOSTOKEN = "<|bos|>"
+EOSTOKEN = "<|eos|>"
+PADTOKEN = "<|pad|>"
+
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+
+
+SPECIAL_START_ID = 127957
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    # with open(tiktoken_bpe_file, "rb", encoding="utf-8") as f:
+    #     contents = f.read()
+    dic = {}
+    rank = 0
+    for line in open(tiktoken_bpe_file, "rb"):
+        if line:
+            token, _ = line.split()
+            if base64.b64decode(token) in dic:
+                continue
+            dic[base64.b64decode(token)] = int(rank)
+            rank += 1
+    global SPECIAL_START_ID
+    SPECIAL_START_ID=rank
+    return dic
+
+# NOTE: Please use the code line to check `SPECIAL_START_ID` right, this will affect the SPECIAL_START_ID
+# _load_tiktoken_bpe('/apdcephfs/share_1502809/shaneshu/tokenizer_exp/other_tokenizer_vocab/hy/' + VOCAB_FILES_NAMES['vocab_file'])
+# print(SPECIAL_START_ID)
+
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                STARTOFTEXT,
+                BOSTOKEN,
+                EOSTOKEN,
+                PADTOKEN,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+# NOTE: Unused Token ID starts from 127962
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+class HYTokenizer(PreTrainedTokenizer):
+    """hunyuan tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "HunYuan",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks)} + {len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.bod_id = self.special_tokens[STARTOFTEXT]
+        self.bos_id = self.special_tokens[BOSTOKEN]
+        self.eos_id = self.special_tokens[EOSTOKEN]
+        self.pad_id = self.special_tokens[PADTOKEN]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "HunYuan",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "hunyuan.tiktoken")
+        with open(file_path, "w", encoding="utf-8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf-8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)
+
+# tests
+if __name__ == "__main__":
+    tokenizer = HYTokenizer.from_pretrained('./hy')
+    text = '你好，世界'
+    tokens = tokenizer.tokenize(text)
+    print(tokens)
+    ids = tokenizer.convert_tokens_to_ids(tokens)
+    print(ids)
+    text2 = tokenizer.convert_tokens_to_string(tokens)
+    print(text2)
+    ids2 = tokenizer.convert_tokens_to_ids(tokens)

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "added_tokens_decoder": {},
+  "additional_special_tokens": [
+    "<|startoftext|>",
+    "<|extra_0|>",
+    "<|extra_4|>",
+    "<|extra_5|>",
+    "<|eos|>"
+  ],
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_hy.HYTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1048576,
+  "model_type": "gpt2",
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "HYTokenizer"
+}