Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|role_start|>system<|role_end|>你是Megrez-3B-Instruct，将针对用户的问题给出详细的、积极的回答。<|turn_end|>' }}{% endif %}{{ '<|role_start|>' + message['role'] + '<|role_end|>' + message['content'] + '<|turn_end|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|role_start|>assistant<|role_end|>' }}{% endif %}

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "MegrezMoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_megrez_moe.MegrezMoeConfig",
+    "AutoModel": "modeling_megrez_moe.MegrezMoeModel",
+    "AutoModelForCausalLM": "modeling_megrez_moe.MegrezMoeForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 120005,
+  "ep_size": 1,
+  "experts_shared_frequency": 3,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 163840,
+  "model_type": "megrez_moe",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 4,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 31,
+  "num_key_value_heads": 4,
+  "pad_token_id": 120002,
+  "pre_gate": true,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 128880
+}

configuration_megrez_moe.py

@@ -0,0 +1,203 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+MegrezMoe_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class MegrezMoeConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`MegrezMoeModel`]. 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-V2.
+
+    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 102400):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`MegrezMoeModel`]
+        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_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 MegrezMoeModel, MegrezMoeConfig
+
+    >>> # Initializing a Deepseek-V2 style configuration
+    >>> configuration = MegrezMoeConfig()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "megrez_moe"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=102400,
+        hidden_size=4096,
+        intermediate_size=11008,
+        moe_intermediate_size=1407,
+        num_hidden_layers=30,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        n_shared_experts=None,
+        n_routed_experts=None,
+        ep_size=1,
+        routed_scaling_factor=1.0,
+        topk_method="gready",
+        n_group=None,
+        topk_group=None,
+        num_experts_per_tok=None,
+        moe_layer_freq=1,
+        first_k_dense_replace=0,
+        norm_topk_prob=False,
+        scoring_func="softmax",
+        aux_loss_alpha=0.001,
+        seq_aux=True,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=100000,
+        eos_token_id=100001,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        experts_shared_frequency=1,
+        pre_gate=False,
+        **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_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.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
+
+        self.experts_shared_frequency = experts_shared_frequency
+        self.pre_gate = pre_gate
+
+        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,
+        )

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ee5723e591719fd3595ca45384f8372ad88a86b1e6100019c3fdb4b9c17af5
+size 4662919784

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41749986f64ff23991b209c761ebcb2fd5cad13f17f364a4b61303851a129cb
+size 4798285336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df54a7ba0c313d1bc90df6c3af4b3718b60f3a395189e5d5f95af33e86bbc31c
+size 4798285344

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5916fe7f39eabb7570cde9938768e3830c90e71b2726df1798aa0afd178bc82a
+size 738197768

model.safetensors.index.json

@@ -0,0 +1,349 @@
+{
+  "metadata": {
+    "total_size": 14997647360
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.experts.gate_proj": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.experts.up_proj": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.experts.gate_proj": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.experts.up_proj": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.experts.gate_proj": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.experts.up_proj": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.experts.gate_proj": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.experts.up_proj": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.experts.gate_proj": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.experts.up_proj": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.experts.gate_proj": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.experts.up_proj": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.experts.down_proj": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.experts.gate_proj": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.experts.up_proj": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.experts.down_proj": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.experts.gate_proj": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.experts.up_proj": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.experts.gate_proj": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.experts.up_proj": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.experts.gate_proj": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.experts.up_proj": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00001-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|turn_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,220 @@
+{
+  "add_bos_token": false,
+  "added_tokens_decoder": {
+    "120000": {
+      "content": "<|eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120001": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120002": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120003": {
+      "content": "<|role_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120004": {
+      "content": "<|role_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120005": {
+      "content": "<|turn_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120006": {
+      "content": "<|code_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120007": {
+      "content": "<|code_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120008": {
+      "content": "<|commit_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120009": {
+      "content": "<|commit_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120010": {
+      "content": "<|diff_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120011": {
+      "content": "<|diff_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120012": {
+      "content": "<|code_execution_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120013": {
+      "content": "<|code_execution_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120014": {
+      "content": "<|image_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120015": {
+      "content": "<|image_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120016": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120017": {
+      "content": "<|video_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120018": {
+      "content": "<|video_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120019": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120020": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120021": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120022": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120023": {
+      "content": "<|function_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120024": {
+      "content": "<|function_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120025": {
+      "content": "<|turn_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|turn_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}