Upload 12 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+models/glm6b-kv-cache-dy-bs8.ftm filter=lfs diff=lfs merge=lfs -text

demo.py

@@ -0,0 +1,47 @@
+
+
+from transformers import AutoTokenizer
+from faster_chat_glm import GLM6B, FasterChatGLM
+
+
+MAX_OUT_LEN = 50
+BATCH_SIZE = 8
+USE_CACHE = True
+
+print("Prepare config and inputs....")
+chatglm6b_dir = './models'
+tokenizer = AutoTokenizer.from_pretrained(chatglm6b_dir, trust_remote_code=True)
+
+input_str = ["音乐推荐应该考虑哪些因素？帮我写一篇不少于800字的方案。 ", ] * BATCH_SIZE
+inputs = tokenizer(input_str, return_tensors="pt", padding=True)
+input_ids = inputs.input_ids
+input_ids = input_ids.to('cuda:0')
+print(input_ids.shape)
+
+
+print('Loading faster model...')
+if USE_CACHE:
+    plan_path = f'./models/glm6b-kv-cache-dy-bs{BATCH_SIZE}.ftm'
+else:
+    plan_path = f'./models/glm6b-bs{BATCH_SIZE}.ftm'
+
+# kernel for chat model.
+kernel = GLM6B(plan_path=plan_path,
+               batch_size=BATCH_SIZE,
+               num_beams=1,
+               use_cache=USE_CACHE,
+               num_heads=32,
+               emb_size_per_heads=128,
+               decoder_layers=28,
+               vocab_size=150528,
+               max_seq_len=MAX_OUT_LEN)
+print("test")
+chat = FasterChatGLM(model_dir=chatglm6b_dir, kernel=kernel).half().cuda()
+
+# generate
+sample_output = chat.generate(inputs=input_ids, max_length=MAX_OUT_LEN)
+# de-tokenize model output to text
+res = tokenizer.decode(sample_output[0], skip_special_tokens=True)
+print(res)
+res = tokenizer.decode(sample_output[BATCH_SIZE-1], skip_special_tokens=True)
+print(res)

faster_chat_glm/__init__.py

@@ -0,0 +1,7 @@
+import os
+
+os.environ["TORCH_USE_RTLD_GLOBAL"]="YES"
+
+import torch
+from .glm import GLM6B
+from .model import FasterChatGLM

faster_chat_glm/__init__.py~

@@ -0,0 +1,3 @@
+import torch
+from .glm import GLM6B
+from .model import FasterChatGLM

faster_chat_glm/model.py

@@ -0,0 +1,131 @@
+import torch
+from transformers.modeling_outputs import CausalLMOutputWithPast
+from transformers.modeling_utils import PreTrainedModel
+from transformers import AutoConfig
+from typing import Dict, List, Tuple, Union, Optional
+
+
+class FasterChatGLM(PreTrainedModel):
+    def __init__(self, model_dir, kernel, *inputs, **kwargs):
+        config = AutoConfig.from_pretrained(model_dir, trust_remote_code=True)
+        config.n_head = config.num_attention_heads
+        config.n_embd = config.hidden_size
+        config.n_layer = config.num_layers
+        super().__init__(config, *inputs, **kwargs)
+        self.kernel = kernel
+        self.fake_reg = torch.nn.Linear(2, 2)
+        self.position_encoding_2d = True
+
+    def forward(self, input_ids, position_ids, attention_mask, past_key_values, *args, **kwargs):
+        inputs_values = [input_ids, position_ids, attention_mask]
+        if past_key_values is not None:
+            inputs_values = inputs_values + past_key_values
+
+        computed = self.kernel.infer(inputs_values)
+        logits = computed[0]
+        if len(computed) == 1:
+            present_key_values = None
+        else:
+            present_key_values = computed[1:]
+
+        return CausalLMOutputWithPast(logits=logits, past_key_values=present_key_values)
+
+    def get_masks_and_position_ids(self, seq, mask_position, context_length, device, gmask=False):
+        attention_mask = torch.ones((1, context_length, context_length), device=device)
+        attention_mask.tril_()
+        attention_mask[..., :context_length - 1] = 1
+        attention_mask.unsqueeze_(1)
+        attention_mask = (attention_mask < 0.5).bool()
+
+        if self.position_encoding_2d:
+            seq_length = seq.index(150004)
+            position_ids = torch.arange(context_length, dtype=torch.long, device=device)
+            if not gmask:
+                position_ids[seq_length:] = mask_position
+            block_position_ids = torch.cat((
+                torch.zeros(seq_length, dtype=torch.long, device=device),
+                torch.arange(context_length - seq_length, dtype=torch.long, device=device) + 1
+            ))
+            position_ids = torch.stack((position_ids, block_position_ids), dim=0)
+        else:
+            position_ids = torch.arange(context_length, dtype=torch.long, device=device)
+            if not gmask:
+                position_ids[context_length - 1:] = mask_position
+
+        position_ids = position_ids.unsqueeze(0)
+
+        return attention_mask, position_ids
+
+    def prepare_one_sample(self, input_id, mask_token, past, past_key_values, use_gmask):
+
+        seq = input_id.tolist()
+        mask_position = seq.index(mask_token)
+
+        if mask_token not in seq:
+            raise ValueError("You have to add either [MASK] or [gMASK] in your input")
+
+        # only last token for input_ids if past is not None
+        if past is not None or past_key_values is not None:
+            context_length = seq.index(150004)
+            last_token = input_id[-1].unsqueeze(-1).unsqueeze(0)  # 2 dim
+            proc_input_id = last_token
+            if self.position_encoding_2d:
+                position_ids = torch.tensor([[[mask_position], [len(seq) - context_length]]], dtype=torch.long,
+                                            device=input_id.device)
+            else:
+                position_ids = torch.tensor([[mask_position]], dtype=torch.long, device=input_id.device)
+
+            attention_mask = torch.zeros(1, 1, 1, 1, device=input_id.device)
+        else:
+            proc_input_id = input_id.unsqueeze(0)
+            attention_mask, position_ids = self.get_masks_and_position_ids(
+                seq=seq,
+                mask_position=mask_position,
+                context_length=len(seq),
+                device=input_id.device,
+                gmask=use_gmask
+            )
+
+        return (proc_input_id.to(torch.int32), position_ids.to(torch.int32),
+                attention_mask.to(torch.bool))
+
+    def prepare_inputs_for_generation(
+            self,
+            input_ids: torch.LongTensor,
+            past: Optional[torch.Tensor] = None,
+            past_key_values: Optional[torch.Tensor] = None,
+            attention_mask: Optional[torch.Tensor] = None,
+            use_cache: bool = None,
+            **kwargs
+    ) -> dict:
+
+        MASK, gMASK = 150000, 150001
+        mask_token = MASK if MASK in input_ids else gMASK
+        use_gmask = False if MASK in input_ids else gMASK
+
+        batch_input_ids, batch_position_ids, batch_attention_mask = [], [], []
+        for input_id in input_ids:
+            proc_input_id, position_id, attention_mask = self.prepare_one_sample(
+                input_id, mask_token, past, past_key_values, use_gmask)
+            batch_input_ids.append(proc_input_id)
+            batch_position_ids.append(position_id)
+            batch_attention_mask.append(attention_mask)
+
+        batch_input_ids = torch.vstack(batch_input_ids)
+        batch_position_ids = torch.vstack(batch_position_ids)
+        batch_attention_mask = torch.vstack(batch_attention_mask)
+
+        if past is None:
+            past = past_key_values
+
+        if past is not None or past_key_values is not None:
+            self.kernel.set_context_mode(False)
+        else:
+            self.kernel.set_context_mode(self.config.use_cache)
+
+        return {
+            "input_ids": batch_input_ids,
+            "past_key_values": past_key_values,
+            "position_ids": batch_position_ids,
+            "attention_mask": batch_attention_mask
+        }

models/README.md

@@ -0,0 +1,3 @@
+需要从 cos 获取加速后的 GLM6B 模型存放：
+
+wget https://chuangxin-research-1258344705.cos.ap-guangzhou.myqcloud.com/cfs-4a8cd28be/vanewu/glm6b-kv-cache-dy-bs8.ftm?q-sign-algorithm=sha1&q-ak=AKIDBF6i7GCtKWS8ZkgOtACzX3MQDl37xYty&q-sign-time=1680756811;1689396811&q-key-time=1680756811;1689396811&q-header-list=&q-url-param-list=&q-signature=95924587fc3c8268c386db06bdb2bdb537074149

models/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "THUDM/chatglm-6b",
+  "architectures": [
+    "ChatGLMModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "bos_token_id": 150004,
+  "eos_token_id": 150005,
+  "hidden_size": 4096,
+  "inner_hidden_size": 16384,
+  "layernorm_epsilon": 1e-05,
+  "max_sequence_length": 2048,
+  "model_type": "chatglm",
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "position_encoding_2d": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 150528
+}

models/configuration_chatglm.py

@@ -0,0 +1,92 @@
+""" ChatGLM model configuration """
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class ChatGLMConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`~ChatGLMModel`].
+    It is used to instantiate an ChatGLM model according to the specified arguments, defining the model
+    architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
+    the ChatGLM-6B [THUDM/ChatGLM-6B](https://huggingface.co/THUDM/chatglm-6b) architecture.
+
+    Configuration objects inherit from  [`PretrainedConfig`] and can be used
+    to control the model outputs. Read the documentation from  [`PretrainedConfig`]
+    for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 150528):
+            Vocabulary size of the ChatGLM-6B model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`~ChatGLMModel`] or
+            [`~TFChatGLMModel`].
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the encoder layers and the pooler layer.
+        num_hidden_layers (`int`, *optional*, defaults to 28):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        inner_hidden_size (`int`, *optional*, defaults to 16384):
+            Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        max_sequence_length (`int`, *optional*, defaults to 512):
+            The maximum sequence length that this model might ever be used with.
+            Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
+        layernorm_epsilon (`float`, *optional*, defaults to 1e-5):
+            The epsilon used by the layer normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether the model should return the last key/values attentions (not used by all models).
+        Example:
+
+    ```python
+    >>> from configuration_chatglm import ChatGLMConfig
+    >>> from modeling_chatglm import ChatGLMModel
+
+    >>> # Initializing a ChatGLM-6B THUDM/ChatGLM-6B style configuration
+    >>> configuration = ChatGLMConfig()
+
+    >>> # Initializing a model from the THUDM/ChatGLM-6B style configuration
+    >>> model = ChatGLMModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```
+"""
+    model_type = "chatglm"
+
+    def __init__(
+            self,
+            vocab_size=150528,
+            hidden_size=4096,
+            num_layers=28,
+            num_attention_heads=32,
+            layernorm_epsilon=1e-5,
+            use_cache=False,
+            bos_token_id=150004,
+            eos_token_id=150005,
+            pad_token_id=0,
+            max_sequence_length=2048,
+            inner_hidden_size=16384,
+            position_encoding_2d=True,
+            **kwargs
+    ):
+        self.num_layers = num_layers
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_attention_heads = num_attention_heads
+        self.max_sequence_length = max_sequence_length
+        self.layernorm_epsilon = layernorm_epsilon
+        self.inner_hidden_size = inner_hidden_size
+        self.use_cache = use_cache
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+        self.pad_token_id = pad_token_id
+        self.position_encoding_2d = position_encoding_2d
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            **kwargs
+        )

models/glm6b-kv-cache-dy-bs8.ftm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e97fb542110a3a226058eb76b6019bbaf91d3165da6ac95aa3976ee75b0421
+size 14706031108

models/ice_text.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99871e0c85db81ad7af1028854fd091cd5778c8414ae9d94bbbc10d02c831c21
+size 2699926

models/tokenization_chatglm.py

@@ -0,0 +1,346 @@
+"""Tokenization classes for ChatGLM."""
+import sys
+import unicodedata
+from typing import List, Optional, Union
+from functools import lru_cache
+import os
+import collections
+import re
+
+from transformers.tokenization_utils import PreTrainedTokenizer
+from icetk.text_tokenizer import TextTokenizer
+from icetk.utils import auto_create
+import icetk.sentencepiece_model_pb2 as sp_model
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
+    "THUDM/chatglm-6b": 2048,
+}
+
+
+class SPTokenizer:
+    def __init__(
+        self,
+        vocab_file,
+        max_blank_length=80,
+        byte_fallback=True,
+    ):
+        assert vocab_file is not None
+        self.vocab_file = vocab_file
+        self.special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "<unused_0>", "<sop>", "<eop>", "<ENC>", "<dBLOCK>"]
+        self.max_blank_length = max_blank_length
+        self.byte_fallback = byte_fallback
+        self.text_tokenizer = self._build_text_tokenizer(encode_special_tokens=False)
+        self.special_text_tokenizer = self._build_text_tokenizer(encode_special_tokens=True)
+
+    @staticmethod
+    def _configure_tokenizer(
+        text_tokenizer: TextTokenizer,
+        special_tokens: List[str],
+        max_blank_length: int,
+        byte_fallback: bool,
+        encode_special_tokens=False,
+    ):
+        # special token
+        special_token_type = 4 if encode_special_tokens else 3  # 3 - CONTROL, 4 - USER_DEFINE
+        for token in special_tokens:
+            text_tokenizer.proto.pieces.append(
+                sp_model.ModelProto.SentencePiece(piece=token, score=0.0, type=special_token_type)
+            )
+        # whitespaces
+        for token in [SPTokenizer.get_tab_token()] + [
+            SPTokenizer.get_blank_token(i) for i in range(2, max_blank_length + 1)
+        ]:
+            text_tokenizer.proto.pieces.append(sp_model.ModelProto.SentencePiece(piece=token, score=0.0, type=4))
+        # byte fallback
+        if byte_fallback:
+            text_tokenizer.proto.trainer_spec.byte_fallback = True
+            for i in range(256):
+                text_tokenizer.proto.pieces.append(
+                    sp_model.ModelProto.SentencePiece(piece="<0x{:02X}>".format(i), score=0.0, type=6)
+                )
+        text_tokenizer.refresh()
+
+    def _build_text_tokenizer(self, encode_special_tokens=False):
+        tokenizer = TextTokenizer(self.vocab_file)
+        self._configure_tokenizer(
+            tokenizer, self.special_tokens, self.max_blank_length, self.byte_fallback, encode_special_tokens
+        )
+        return tokenizer
+
+    def _get_text_tokenizer(self, encode_special_tokens=False):
+        if encode_special_tokens:
+            return self.special_text_tokenizer
+        else:
+            return self.text_tokenizer
+
+    @staticmethod
+    def get_blank_token(length: int):
+        assert length >= 2
+        return f"<|blank_{length}|>"
+
+    @staticmethod
+    def get_tab_token():
+        return f"<|tab|>"
+
+    @property
+    def num_image_tokens(self):
+        return 20000
+
+    @property
+    def num_text_tokens(self):
+        return self.text_tokenizer.num_tokens
+
+    @property
+    def num_tokens(self):
+        return self.num_image_tokens + self.num_text_tokens
+
+    @staticmethod
+    def _encode_whitespaces(text: str, max_len: int = 80):
+        text = text.replace("\t", SPTokenizer.get_tab_token())
+        for i in range(max_len, 1, -1):
+            text = text.replace(" " * i, SPTokenizer.get_blank_token(i))
+        return text
+
+    def _preprocess(self, text: str, linebreak=True, whitespaces=True):
+        if linebreak:
+            text = text.replace("\n", "<n>")
+        if whitespaces:
+            text = self._encode_whitespaces(text, max_len=self.max_blank_length)
+        return text
+
+    def encode(
+        self, text: str, linebreak=True, whitespaces=True, special_tokens=False, add_dummy_prefix=True
+    ) -> List[int]:
+        """
+        @param text: Text to encode.
+        @param linebreak: Whether to encode newline (\n) in text.
+        @param whitespaces: Whether to encode multiple whitespaces or tab in text, useful for source code encoding.
+        @param special_tokens: Whether to encode special token ([MASK], [gMASK], etc.) in text.
+        @param add_dummy_prefix: Whether to add dummy blank space in the beginning.
+        """
+        text = self._preprocess(text, linebreak, whitespaces)
+        if not add_dummy_prefix:
+            text = "<n>" + text
+        tmp = self._get_text_tokenizer(encode_special_tokens=special_tokens).encode(text)
+        tokens = [x + self.num_image_tokens for x in tmp]
+        return tokens if add_dummy_prefix else tokens[2:]
+
+    def decode(self, text_ids: List[int], special_tokens=False) -> str:
+        ids = [int(_id) - self.num_image_tokens for _id in text_ids]
+        ids = [_id for _id in ids if _id >= 0]
+        text = self._get_text_tokenizer(encode_special_tokens=special_tokens).decode(ids)
+        text = text.replace("<n>", "\n")
+        text = text.replace(SPTokenizer.get_tab_token(), "\t")
+        for i in range(2, self.max_blank_length + 1):
+            text = text.replace(self.get_blank_token(i), " " * i)
+        return text
+
+    def tokenize(
+        self, text: str, linebreak=True, whitespaces=True, special_tokens=False, add_dummy_prefix=True
+    ) -> List[str]:
+        """
+        @param text: Text to encode.
+        @param linebreak: Whether to encode newline (\n) in text.
+        @param whitespaces: Whether to encode multiple whitespaces or tab in text, useful for source code encoding.
+        @param special_tokens: Whether to encode special token ([MASK], [gMASK], etc.) in text.
+        @param add_dummy_prefix: Whether to add dummy blank space in the beginning.
+        """
+        text = self._preprocess(text, linebreak, whitespaces)
+        if not add_dummy_prefix:
+            text = "<n>" + text
+        tokens = self._get_text_tokenizer(encode_special_tokens=special_tokens).tokenize(text)
+        return tokens if add_dummy_prefix else tokens[2:]
+
+    def __getitem__(self, x: Union[int, str]):
+        if isinstance(x, int):
+            if x < self.num_image_tokens:
+                return "<image_{}>".format(x)
+            else:
+                return self.text_tokenizer.convert_id_to_token(x - self.num_image_tokens)
+        elif isinstance(x, str):
+            if x.startswith("<image_") and x.endswith(">") and x[7:-1].isdigit():
+                return int(x[7:-1])
+            else:
+                return self.text_tokenizer.convert_token_to_id(x) + self.num_image_tokens
+        else:
+            raise ValueError("The key should be str or int.")
+
+
+class ChatGLMTokenizer(PreTrainedTokenizer):
+    """
+    Construct a ChatGLM tokenizer. Based on byte-level Byte-Pair-Encoding.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+    """
+
+    vocab_files_names = {"vocab_file": "ice_text.model"}
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids"]
+
+    def __init__(
+            self,
+            vocab_file,
+            do_lower_case=False,
+            remove_space=False,
+            bos_token='sop',
+            eos_token='eos',
+            eop_token='eop',
+            mask_token='[MASK]',
+            gmask_token='[gMASK]',
+            padding_side="left",
+            **kwargs
+    ) -> None:
+        super().__init__(
+            do_lower_case=do_lower_case,
+            remove_space=remove_space,
+            padding_side=padding_side,
+            **kwargs
+        )
+
+        self.do_lower_case = do_lower_case
+        self.remove_space = remove_space
+        self.vocab_file = vocab_file
+
+        self.bos_token = bos_token
+        self.eos_token = eos_token
+        self.eop_token = eop_token
+        self.mask_token = mask_token
+        self.gMASK_token = gmask_token
+
+        self.sp_tokenizer = SPTokenizer(vocab_file)
+
+        """ Initialisation """
+
+    @property
+    def eop_token_id(self) -> Optional[int]:
+        """
+        `Optional[int]`: Id of the end of sentence token in the vocabulary. Returns `None` if the token has not been
+        set.
+        """
+        if self.eop_token is None:
+            return None
+        return self.convert_tokens_to_ids(self.eop_token)
+
+    @property
+    def vocab_size(self):
+        """ Returns vocab size """
+        return self.sp_tokenizer.num_tokens
+
+    def get_vocab(self):
+        """ Returns vocab as a dict """
+        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def preprocess_text(self, inputs):
+        if self.remove_space:
+            outputs = " ".join(inputs.strip().split())
+        else:
+            outputs = inputs
+
+        if self.do_lower_case:
+            outputs = outputs.lower()
+
+        return outputs
+
+    def _tokenize(self, text, **kwargs):
+        """ Returns a tokenized string. """
+        text = self.preprocess_text(text)
+
+        seq = self.sp_tokenizer.tokenize(text)
+
+        return seq
+
+    def decode(
+            self,
+            token_ids: Union[List[int], List[List[int]]],
+            skip_special_tokens: bool = False,
+            clean_up_tokenization_spaces: bool = True,
+            spaces_between_special_tokens: bool = True,
+            **kwargs
+    ) -> str:
+        if isinstance(token_ids[0], list):
+            tokens = []
+            for single_token_ids in token_ids:
+                if self.pad_token_id in single_token_ids:  # remove pad
+                    single_token_ids = list(filter((self.pad_token_id).__ne__, single_token_ids))
+                tokens.append(self.sp_tokenizer.decode(single_token_ids))
+            return (tokens)
+        else:
+            if self.pad_token_id in token_ids:  # remove pad
+                token_ids = list(filter((self.pad_token_id).__ne__, token_ids))
+            return self.sp_tokenizer.decode(token_ids)
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.sp_tokenizer[token]
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.sp_tokenizer[index]
+
+    def save_vocabulary(self, save_directory, filename_prefix=None):
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+            filename_prefix (`str`, *optional*):
+                An optional prefix to add to the named of the saved files.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if os.path.isdir(save_directory):
+            vocab_file = os.path.join(
+                save_directory, VOCAB_FILES_NAMES["vocab_file"]
+            )
+        else:
+            vocab_file = save_directory
+
+        with open(self.vocab_file, 'rb') as fin:
+            proto_str = fin.read()
+
+        with open(vocab_file, "wb") as writer:
+            writer.write(proto_str)
+
+        return (vocab_file,)
+
+    def build_inputs_with_special_tokens(
+            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A BERT sequence has the following format:
+
+        - single sequence: `[CLS] X [SEP]`
+        - pair of sequences: `[CLS] A [SEP] B [SEP]`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+        if token_ids_1 is not None:
+            token_ids_0 += token_ids_1
+        mask_ids = self.sp_tokenizer[self.mask_token]
+        gmask_ids = self.sp_tokenizer[self.gMASK_token]
+        if mask_ids not in token_ids_0 and gmask_ids not in token_ids_0:
+            token_ids_0 += [gmask_ids]
+
+        if token_ids_0[-1] != mask_ids and token_ids_0[-1] != gmask_ids:
+            token_ids_0 += [self.sp_tokenizer[self.eos_token]]
+
+        token_ids_0 += [self.sp_tokenizer[self.bos_token]]
+
+        return token_ids_0

models/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "name_or_path": "THUDM/chatglm-6b",
+  "bos_token": "<sop>",
+  "eop_token": "<eop>",
+  "eos_token": "</s>",
+  "gmask_token": "[gMASK]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>",
+  "remove_space": false,
+  "do_lower_case": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLMTokenizer",
+      null
+      ]
+  }
+}