Add files using upload-large-folder tool

chat_template.jinja

@@ -0,0 +1,112 @@
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{%- set default_system = "你是中国电信星辰语义大模型，英文名是Xing，你是由中电信人工智能科技有限公司研发的人工智能助手。\n" %}
+{%- if system_message is defined %}
+    {{- "<_system>" + visible_text(system_message) }}
+{%- else %}
+    {{- "<_system>" + default_system }}
+{%- endif %}
+{% if tools is iterable and tools | length > 0 %}
+
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<param_key>{param-key-1}</param_key><param_value>{param-value-1}</param_value><param_key>{param-key-2}</param_key><param_value>{param-value-2}</param_value>...</tool_call>
+{%- endif %}
+
+
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in loop_messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{%- for m in loop_messages %}
+{%- if m.role == 'user' -%}<_user>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' or m.role == 'bot' -%}
+<_bot>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+{%- set reasoning_content = m.reasoning_content %}
+{%- elif m.reasoning is string %}
+{%- set reasoning_content = m.reasoning %}
+{%- else %}
+{%- if '</think>' in content %}
+{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+{%- set content = content.split('</think>')[-1].lstrip('\n') %}
+{%- endif %}
+{%- endif %}
+{%- if loop.index0 < ns.last_user_index -%}
+{{ '</think>' }}
+{%- elif enable_thinking is not defined or enable_thinking -%}
+{{ '<think>\n' + reasoning_content.strip() +  '\n</think>'}}
+{%- else -%}
+{{ '</think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{%- for tc in m.tool_calls %}
+{%- if tc.function %}
+{%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}
+{%- for k, v in _args.items() %}<param_key>{{ k }}</param_key><param_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</param_value>{% endfor %}{{ '</tool_call>' }}{% endfor %}{% endif %}{{- '<_end>\n' }}
+{%- elif m.role == 'tool' -%}
+{%- if loop.index0 > 0 -%}
+{%- set prev_element = loop_messages[loop.index0 - 1] -%}
+{%- if prev_element.role != "tool" -%}
+{{- '<_observation>' -}}
+{%- endif -%}
+{%- endif -%}
+{%- if m.content is string -%}
+{{- '<tool_response>' -}}
+{{- m.content }}
+{{- '</tool_response>' -}}
+{%- else -%}
+{% for tr in m.content %}  
+{{- '<tool_response>' -}}{{ tr.output if tr.output is defined else tr }}{{- '</tool_response>' -}}
+{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<_system>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <_bot>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>\n' -}}
+{%- endif -%}
+

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Xing4_0ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_xing4_0.Xing4_0Config"
+  },
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "ep_size": 1,
+  "first_k_dense_replace": 2,
+  "hc_eps": 1e-06,
+  "hc_mult": 4,
+  "hc_sinkhorn_iters": 20,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 262144,
+  "mhc_h_res_clamp_max": 30,
+  "mhc_h_res_clamp_min": -30,
+  "model_type": "xing4_0",
+  "moe_intermediate_size": 1024,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "num_nextn_predict_layers": 0,
+  "q_lora_rank": 768,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 64,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.0,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.14.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 131072
+}

configuration_xing4_0.py

@@ -0,0 +1,142 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class Xing4_0Config(PretrainedConfig):
+    model_type = "xing4_0"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    base_model_tp_plan = {
+        "layers.*.mlp.experts.gate_up_proj": "packed_colwise",
+        "layers.*.mlp.experts.down_proj": "rowwise",
+        "layers.*.mlp.experts": "moe_tp_experts",
+        "layers.*.mlp.shared_experts.gate_proj": "colwise",
+        "layers.*.mlp.shared_experts.up_proj": "colwise",
+        "layers.*.mlp.shared_experts.down_proj": "rowwise",
+        "layers.*.mlp.gate_proj": "colwise",
+        "layers.*.mlp.up_proj": "colwise",
+        "layers.*.mlp.down_proj": "rowwise",
+    }
+    base_model_pp_plan = {
+        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
+        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
+        "norm": (["hidden_states"], ["hidden_states"]),
+    }
+    base_model_ep_plan = {
+        "layers.*.mlp.gate": "ep_router",
+        "layers.*.mlp.experts.gate_up_proj": "grouped_gemm",
+        "layers.*.mlp.experts.down_proj": "grouped_gemm",
+        "layers.*.mlp.experts": "moe_tp_experts",
+    }
+
+    attribute_map = {
+        "num_local_experts": "n_routed_experts",
+        "num_mtp_layers": "num_nextn_predict_layers",
+    }
+
+    def __init__(
+            self,
+            vocab_size=131072,
+            hidden_size=3584,
+            intermediate_size=9216,
+            moe_intermediate_size=1024,
+            num_hidden_layers=40,
+            num_nextn_predict_layers=1,
+            num_attention_heads=32,
+            num_key_value_heads=32,
+            n_shared_experts=1,
+            n_routed_experts=64,
+            ep_size=1,
+            routed_scaling_factor=2.0,
+            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=4,
+            moe_layer_freq=1,
+            first_k_dense_replace=2,
+            norm_topk_prob=True,
+            scoring_func='sigmoid',
+            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=1,
+            eos_token_id=2,
+            tie_word_embeddings=False,
+            rope_theta=10000.0,
+            rope_scaling=None,
+            rope_interleave=True,
+            attention_bias=False,
+            attention_dropout=0.0,
+            hc_mult: int = 4,
+            hc_sinkhorn_iters: int = 20,
+            hc_eps: float = 1.0e-6,
+            mhc_h_res_clamp_min=-30,
+            mhc_h_res_clamp_max=30,
+            **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.qk_head_dim = self.qk_nope_head_dim + self.qk_rope_head_dim
+        self.head_dim = self.qk_rope_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
+        # 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.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        self.hc_mult = hc_mult
+        self.hc_sinkhorn_iters = hc_sinkhorn_iters
+        self.hc_eps = hc_eps
+        self.mhc_h_res_clamp_min = mhc_h_res_clamp_min
+        self.mhc_h_res_clamp_max = mhc_h_res_clamp_max
+        self.rope_interleave = rope_interleave
+        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,
+        )
+
+

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "do_sample": true,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "repetition_penalty": 1.05,
+  "transformers_version": "4.48.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0743b88189def95babc06322e6ec378f161776a6075081f61b1c1d868a2277
+size 5315029228

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e132a4e086993ddebaef112721fe95be3e1c3dc4569445d1dd1be4e26d758ef3
+size 5332993813

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222a5d9bb8719d5c624a505108f8dab8212b992698b64778609d9c798a108f0b
+size 5332993755

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4f846469fe5ae875b9c63cc15b2292690bfc815d3c59a4194eaa3f756ce634
+size 668656619

tokenization_xing4_0.py

@@ -0,0 +1,222 @@
+import os
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple
+import sentencepiece as spm
+from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
+
+# TODO: when we get download url from huggingface, refresh the map
+PRETRAINED_VOCAB_FILES_MAP = {
+    "vocab_file": {},
+    "tokenizer_file": {},
+}
+
+
+class Xing4_0Tokenizer(PreTrainedTokenizer):
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+            self,
+            vocab_file,
+            unk_token="<unk>",
+            bos_token="<_start>",
+            eos_token="<_end>",
+            pad_token="<_pad>",
+            sp_model_kwargs: Optional[Dict[str, Any]] = None,
+            add_bos_token=True,
+            add_eos_token=False,
+            clean_up_tokenization_spaces=False,
+            **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
+        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_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,
+            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,
+            **kwargs,
+        )
+        self.vocab_file = vocab_file
+        self.add_bos_token = add_bos_token
+        self.add_eos_token = add_eos_token
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        state["sp_model"] = None
+        return state
+
+    def __setstate__(self, d):
+        self.__dict__ = d
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(self.vocab_file)
+
+    @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
+
+    @property
+    def vocab(self):
+        return self.get_vocab()
+
+    def _tokenize(self, text):
+        """Returns a tokenized string."""
+        return self.sp_model.encode(text, out_type=str)
+
+    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):
+            # make sure that special tokens are not decoded using sentencepiece model
+            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]:
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        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]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        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]:
+        """
+        Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
+        sequence pair mask has the following format:
+
+        ```
+        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+        | first sequence    | second sequence |
+        ```
+
+        if token_ids_1 is None, only returns the first portion of the mask (0s).
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of ids.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
+        """
+        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
+

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcbbfdf8655a2e8b8a9fe478de0e9347e857c9b043f9752d04ed660286c3ac5
+size 2199270

tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<_user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<_bot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<_system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_xing4_0.Xing4_0Tokenizer",
+      null
+    ]
+  },
+  "backend": "custom",
+  "bos_token": "<_start>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<_end>",
+  "extra_special_tokens": [
+    "<_start>",
+    "<_end>",
+    "<_pad>",
+    "<_user>",
+    "<_bot>",
+    "<_system>",
+    "<think>",
+    "</think>",
+    "<tool_call>",
+    "</tool_call>",
+    "<tool_response>",
+    "</tool_response>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 100000000,
+  "pad_token": "<_pad>",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "Xing4_0Tokenizer",
+  "use_fast": false
+}