Upload 5 files

models/Kimi-VL-A3B/config.json

@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "KimiVLForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_kimi_vl.KimiVLConfig",
+    "AutoModel": "modeling_kimi_vl.KimiVLForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_kimi_vl.KimiVLForConditionalGeneration"
+  },
+  "vision_config": {
+    "model_type": "moonvit",
+    "patch_size": 14,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "init_pos_emb_height": 64,
+    "init_pos_emb_width": 64,
+    "merge_kernel_size": [
+      2,
+      2
+    ],
+    "torch_dtype": "bfloat16"
+  },
+  "text_config": {
+    "vocab_size": 163840,
+    "max_position_embeddings": 131072,
+    "hidden_size": 2048,
+    "intermediate_size": 11264,
+    "moe_intermediate_size": 1408,
+    "num_hidden_layers": 27,
+    "num_attention_heads": 16,
+    "n_shared_experts": 2,
+    "n_routed_experts": 64,
+    "ep_size": 1,
+    "routed_scaling_factor": 2.446,
+    "kv_lora_rank": 512,
+    "q_lora_rank": null,
+    "qk_rope_head_dim": 64,
+    "v_head_dim": 128,
+    "qk_nope_head_dim": 128,
+    "topk_method": "noaux_tc",
+    "n_group": 1,
+    "topk_group": 1,
+    "num_experts_per_tok": 6,
+    "moe_layer_freq": 1,
+    "first_k_dense_replace": 1,
+    "norm_topk_prob": true,
+    "scoring_func": "sigmoid",
+    "aux_loss_alpha": 0.001,
+    "seq_aux": true,
+    "num_key_value_heads": 16,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 800000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 163584,
+    "pad_token_id": 163839,
+    "eos_token_id": 163585,
+    "torch_dtype": "bfloat16",
+    "tie_word_embeddings": false
+  },
+  "ignore_index": -100,
+  "media_placeholder_token_id": 163605,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
+  "tie_word_embeddings": false,
+  "vocab_size": 163840,
+  "model_type": "kimi_vl"
+}

models/Kimi-VL-A3B/configuration_kimi_vl.py

@@ -0,0 +1,284 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+from typing import Optional, Union
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    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 DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Copy from https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/configuration_deepseek.py
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size=2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts=1,
+        n_routed_experts=256,
+        ep_size=1,
+        routed_scaling_factor=2.5,
+        kv_lora_rank=512,
+        q_lora_rank=1536,
+        qk_rope_head_dim=64,
+        v_head_dim=128,
+        qk_nope_head_dim=128,
+        topk_method="noaux_tc",
+        n_group=8,
+        topk_group=4,
+        num_experts_per_tok=8,
+        moe_layer_freq=1,
+        first_k_dense_replace=3,
+        norm_topk_prob=True,
+        scoring_func="sigmoid",
+        aux_loss_alpha=0.001,
+        seq_aux=True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+
+class MoonViTConfig(PretrainedConfig):
+    model_type = "moonvit"
+
+    def __init__(
+        self,
+        patch_size: int = 14,
+        init_pos_emb_height: int = 64,
+        init_pos_emb_width: int = 64,
+        num_attention_heads: int = 16,
+        num_hidden_layers: int = 27,
+        hidden_size: int = 1152,
+        intermediate_size: int = 4304,
+        merge_kernel_size: tuple[int, int] = (2, 2),
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.patch_size = patch_size
+        # Positional embedding config
+        self.init_pos_emb_height = init_pos_emb_height
+        self.init_pos_emb_width = init_pos_emb_width
+        # Transformer config
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        # Patch merger config
+        self.merge_kernel_size = merge_kernel_size
+
+
+class KimiVLConfig(PretrainedConfig):
+    model_type = "kimi_vl"
+
+    def __init__(
+        self,
+        vision_config: Optional[Union[dict, MoonViTConfig]] = None,
+        text_config: Optional[Union[dict, DeepseekV3Config]] = None,
+        ignore_index: int = -100,
+        media_placeholder_token_id: int = 163605,
+        pad_token_id: int = 0,
+        **kwargs,
+    ):
+        if vision_config is None:
+            vision_config = MoonViTConfig()
+        elif isinstance(vision_config, dict):
+            vision_config = MoonViTConfig(**vision_config)
+        self.vision_config = vision_config
+
+        if text_config is None:
+            text_config = DeepseekV3Config()
+        elif isinstance(text_config, dict):
+            text_config = DeepseekV3Config(**text_config)
+        self.text_config = text_config
+
+        self.ignore_index = ignore_index
+        self.media_placeholder_token_id = media_placeholder_token_id
+
+        attn_implementation = kwargs.get("attn_implementation")
+        if attn_implementation is not None:
+            if attn_implementation in ["eager", "flash_attention_2"]:
+                self._attn_implementation = attn_implementation
+                self.vision_config._attn_implementation = attn_implementation
+                self.text_config._attn_implementation = attn_implementation
+            else:
+                raise ValueError(
+                    f"Invalid attention implementation: {attn_implementation}"
+                )
+
+        super().__init__(pad_token_id=pad_token_id, **kwargs)

models/Kimi-VL-A3B/tiktoken.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103
+size 2795286

models/Kimi-VL-A3B/tokenization_moonshot.py

@@ -0,0 +1,312 @@
+import os
+import tiktoken
+
+from logging import getLogger
+from pathlib import Path
+from typing import (
+    cast,
+    Tuple,
+    Dict,
+    Iterator,
+    List,
+    Union,
+    Optional,
+)
+from shutil import copyfile
+from tiktoken.load import load_tiktoken_bpe
+from tokenizers import AddedToken
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.utils import to_py_obj
+from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
+
+
+logger = getLogger(__name__)
+VOCAB_FILES_NAMES = {"vocab_file": "tiktoken.model"}
+SPIECE_UNDERLINE = "▁"
+
+
+class TikTokenTokenizer(PreTrainedTokenizer):
+    """
+    Tokenizing and encoding/decoding text using the Tiktoken tokenizer. See megatron/tokenizer/tiktoken_tokenizer.py.
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
+
+    Args:
+        vocab_file (`str`):
+            The path to the Tiktoken model file.
+        bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|begin_of_text|>",`):
+            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 `"<|end_of_text|>"`):
+            The end of sequence token.
+        unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|reserved_special_token_249|>"`):
+            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. The second to last item in special_tokens.
+        pad_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|reserved_special_token_250|>"`):
+            The token used for padding, for example when batching sequences of different lengths.
+        additional_special_tokens (list of `str`, *optional*):
+            A tuple or a list of additional tokens, which will be marked as `special`, meaning that they will be
+            skipped when decoding if `skip_special_tokens` is set to `True`.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    model_input_names = ["input_ids", "attention_mask"]
+
+    special_tokens: Dict[str, int]
+
+    num_reserved_special_tokens = 256
+
+    pat_str = "|".join(
+        [
+            r"""[\p{Han}]+""",
+            r"""[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?""",
+            r"""[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?""",
+            r"""\p{N}{1,3}""",
+            r""" ?[^\s\p{L}\p{N}]+[\r\n]*""",
+            r"""\s*[\r\n]+""",
+            r"""\s+(?!\S)""",
+            r"""\s+""",
+        ]
+    )
+
+    def __init__(
+        self,
+        vocab_file,
+        bos_token: Union[str, AddedToken] = "[BOS]",
+        eos_token: Union[str, AddedToken] = "[EOS]",
+        unk_token: Union[str, AddedToken] = "[UNK]",
+        pad_token: Union[str, AddedToken] = "[PAD]",
+        additional_special_tokens: Optional[List[str]] = None,
+        added_tokens_decoder: Optional[dict] = None,
+        **kwargs,
+    ):
+        assert os.path.isfile(vocab_file), vocab_file
+        if additional_special_tokens is None:
+            additional_special_tokens = [
+                "<|im_end|>",
+                "<|im_middle|>",
+                "<|im_user|>",
+                "<|im_assistant|>",
+                "<|im_system|>",
+            ]
+        special_tokens_mapping = {
+            i: added_tokens_decoder[i].content for i in added_tokens_decoder
+        }
+
+        special_tokens = (
+            [str(bos_token), str(eos_token)]
+            + additional_special_tokens
+            + [str(unk_token), str(pad_token)]
+        )
+
+        self.vocab_file = vocab_file
+        mergeable_ranks = load_tiktoken_bpe(vocab_file)
+        num_base_tokens = len(mergeable_ranks)
+        self.special_tokens = {
+            special_tokens_mapping.get(i, f"<|reserved_token_{i}|>"): i
+            for i in range(
+                num_base_tokens, num_base_tokens + self.num_reserved_special_tokens + 2
+            )
+        }
+
+        self.model = tiktoken.Encoding(
+            name=Path(vocab_file).name,
+            pat_str=self.pat_str,
+            mergeable_ranks=mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        logger.info(f"Reloaded tiktoken model from {vocab_file}")
+
+        self.n_words: int = self.model.n_vocab
+        # BOS / EOS token IDs
+        self.bos_id: int = self.special_tokens[str(bos_token)]
+        self.eos_id: int = self.special_tokens[str(eos_token)]
+        logger.info(
+            f"#words: {self.n_words} - BOS ID: {self.bos_id} - EOS ID: {self.eos_id}"
+        )
+
+        self.pad_id: int = self.special_tokens[str(pad_token)]
+        self.unk_id: int = self.special_tokens[str(unk_token)]
+
+        self.byte_encoder = bytes_to_unicode()
+        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
+
+        self.decoder = {}
+        for i in range(self.n_words):
+            # Taken from https://gist.github.com/xenova/a452a6474428de0182b17605a98631ee
+            decoding = "".join(
+                [
+                    self.byte_encoder[ord(char)]
+                    for char in self.model.decode_single_token_bytes(i).decode(
+                        "latin-1"
+                    )
+                ]
+            )
+            self.decoder[i] = decoding
+
+        self.encoder = {}
+        for i in range(self.n_words):
+            if i in self.decoder:
+                self.encoder[self.decoder[i]] = i
+
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            additional_special_tokens=additional_special_tokens,
+            **kwargs,
+        )
+        self.all_special_ids_set = set(self.all_special_ids)
+
+    def encode(
+        self, text: str, allow_special_tokens: bool = True, **kwargs
+    ) -> List[int]:
+        """
+        Encodes a string into a list of token IDs.
+
+        Args:
+            text (str): The input string to be encoded.
+
+        Returns:
+            list[int]: A list of token IDs.
+        """
+        # If there are other args, we should call super().encode because there are a lot of code
+        # to handle those args. supper().encode finally will call _tokenize and _convert_token_to_id.
+        if len(kwargs) > 0:
+            return super().encode(text, **kwargs)
+
+        assert type(text) is str
+
+        # The tiktoken tokenizer can handle <=400k chars without
+        # pyo3_runtime.PanicException.
+        TIKTOKEN_MAX_ENCODE_CHARS = 400_000
+
+        # https://github.com/openai/tiktoken/issues/195
+        # Here we iterate over subsequences and split if we exceed the limit
+        # of max consecutive non-whitespace or whitespace characters.
+        MAX_NO_WHITESPACES_CHARS = 25_000
+
+        substrs = (
+            substr
+            for i in range(0, len(text), TIKTOKEN_MAX_ENCODE_CHARS)
+            for substr in self._split_whitespaces_or_nonwhitespaces(
+                text[i : i + TIKTOKEN_MAX_ENCODE_CHARS], MAX_NO_WHITESPACES_CHARS
+            )
+        )
+        t: List[int] = []
+        for substr in substrs:
+            if allow_special_tokens:
+                t.extend(
+                    # we should consider special token as a common token
+                    self.model.encode(
+                        substr,
+                        allowed_special="all",
+                    )
+                )
+            else:
+                t.extend(
+                    # we should consider special token as a common token
+                    self.model.encode(
+                        substr,
+                        disallowed_special=(),
+                    )
+                )
+        return t
+
+    def decode(self, token_ids: Union[int, List[int]], **kwargs) -> str:
+        """
+        Decodes a list of token IDs into a string.
+
+        Args:
+            t (List[int]): The list of token IDs to be decoded.
+
+        Returns:
+            str: The decoded string.
+        """
+        # If there are other args, we should call super().decode because there are a lot of code
+        # to handle those args. supper().encode finally will call convert_tokens_to_string and _convert_id_to_token.
+        if len(kwargs) > 0:
+            return super().decode(token_ids, **kwargs)
+
+        token_ids = to_py_obj(token_ids)
+
+        if type(token_ids) is int:
+            token_ids = [token_ids]
+
+        return self.model.decode(cast(List[int], token_ids))
+
+    @staticmethod
+    def _split_whitespaces_or_nonwhitespaces(
+        s: str, max_consecutive_slice_len: int
+    ) -> Iterator[str]:
+        """
+        Splits the string `s` so that each substring contains no more than `max_consecutive_slice_len`
+        consecutive whitespaces or consecutive non-whitespaces.
+        """
+        current_slice_len = 0
+        current_slice_is_space = s[0].isspace() if len(s) > 0 else False
+        slice_start = 0
+
+        for i in range(len(s)):
+            is_now_space = s[i].isspace()
+
+            if current_slice_is_space ^ is_now_space:
+                current_slice_len = 1
+                current_slice_is_space = is_now_space
+            else:
+                current_slice_len += 1
+                if current_slice_len > max_consecutive_slice_len:
+                    yield s[slice_start:i]
+                    slice_start = i
+                    current_slice_len = 1
+        yield s[slice_start:]
+
+    """ ----- Below are the abstract methods required by PreTrainedTokenizer ----- """
+
+    @property
+    def vocab_size(self) -> int:
+        return self.n_words
+
+    def get_vocab(self) -> Dict[str, int]:
+        return self.encoder
+
+    def _tokenize(self, text: str, **kwargs) -> List[str]:
+        return [self.decoder[t] for t in self.encode(text)]
+
+    def _convert_token_to_id(self, token: str) -> int:
+        return self.encoder.get(token, self.unk_id)
+
+    def _convert_id_to_token(self, index: int) -> str:
+        return self.decoder.get(index)
+
+    @staticmethod
+    def clean_up_tokenization(out_string: str) -> str:
+        return out_string
+
+    def convert_tokens_to_string(self, tokens: List[str]) -> str:
+        text = "".join(tokens).replace(SPIECE_UNDERLINE, "")
+        text = bytearray([self.byte_decoder[c] for c in text]).decode(
+            "utf-8", "replace"
+        )
+        return text
+
+    def save_vocabulary(
+        self, save_directory: str, 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)
+
+        return (out_vocab_file,)

models/Kimi-VL-A3B/tokenizer_config.json

@@ -0,0 +1,134 @@
+{
+  "added_tokens_decoder": {
+    "163584": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163585": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163586": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163601": {
+      "content": "<|im_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163587": {
+      "content": "<|im_user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163588": {
+      "content": "<|im_assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163594": {
+      "content": "<|im_system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163602": {
+      "content": "<|media_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163603": {
+      "content": "<|media_content|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163604": {
+      "content": "<|media_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163605": {
+      "content": "<|media_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163838": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163839": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|im_system|>",
+    "<|im_middle|>",
+    "<|media_start|>",
+    "<|media_content|>",
+    "<|media_end|>",
+    "<|media_pad|>"
+  ],
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1048576,
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]",
+  "tokenizer_class": "TikTokenTokenizer",
+  "chat_template": "{%- for message in messages -%}{%- if loop.first and messages[0]['role'] != 'system' -%}{{'<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>'}}{%- endif -%}{%- if message['role'] == 'system' -%}{{'<|im_system|>'}}{%- endif -%}{%- if message['role'] == 'user' -%}{{'<|im_user|>'}}{%- endif -%}{%- if message['role'] == 'assistant' -%}{{'<|im_assistant|>'}}{%- endif -%}{{- message['role'] -}}{{'<|im_middle|>'}}{%- if message['content'] is string -%}{{- message['content'] + '<|im_end|>' -}}{%- else -%}{%- for content in message['content'] -%}{%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}{{'<|media_start|>image<|media_content|><|media_pad|><|media_end|>'}}{%- else -%}{{content['text']}}{%- endif -%}{%- endfor -%}{{'<|im_end|>'}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{'<|im_assistant|>assistant<|im_middle|>'}}{%- endif -%}",
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_moonshot.TikTokenTokenizer",
+      null
+    ]
+  }
+}