Add files using upload-large-folder tool

chat_template.jinja

@@ -0,0 +1,96 @@
+{%- macro render_content(msg) -%}
+    {%- set c = msg.get('content') -%}
+    {%- if c is string -%}
+      {{ c }}
+    {%- elif c is not none -%}
+      {% for content in c -%}
+        {% 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 -%}
+    {%- endif -%}
+{%- endmacro -%}
+
+{% macro set_roles(message) -%}
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {%- endif -%}
+{%- endmacro -%}
+
+
+{%- macro render_toolcalls(message) -%}
+  <|tool_calls_section_begin|>
+  {%- for tool_call in message['tool_calls'] -%}
+    {%- set formatted_id = tool_call['id'] -%}
+    <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+  {%- endfor -%}
+  <|tool_calls_section_end|>
+{%- endmacro -%}
+
+
+{# Find last non-tool-call assisitant message #}
+{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
+{%- for idx in range(messages|length-1, -1, -1) -%}
+    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
+        {%- set ns.last_non_tool_call_assistant_msg = idx -%}
+        {%- break -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
+{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
+{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
+
+{%- if tools -%}
+  <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
+{%- endif -%}
+
+{%- for message in hist_msgs -%}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
+  {%- endif -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    <think></think>{{render_content(message)}}
+    {%- if message.get('tool_calls') -%}
+      {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set tool_call_id = message.tool_call_id -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+{%- for message in suffix_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    {%- set rc = message.get('reasoning_content', '') -%}
+    <think>{{rc}}</think>{{render_content(message)}}
+    {%- if message.get('tool_calls') -%}
+     {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set tool_call_id = message.tool_call_id -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+{%- endif -%}

config.json

@@ -0,0 +1,99 @@
+{
+  "_attn_implementation_autoset": false,
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 163584,
+  "dtype": "bfloat16",
+  "eos_token_id": 163586,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 262144,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 384,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 0,
+  "pad_token_id": 163839,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": null,
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head",
+      "re:.*self_attn.*",
+      "re:.*shared_experts.*",
+      "re:.*mlp\\.(gate|up|gate_up|down)_proj.*"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {}
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 1.0,
+    "beta_slow": 1.0,
+    "factor": 64.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 50000.0,
+  "routed_scaling_factor": 2.827,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 163840
+}

configuration_deepseek.py

@@ -0,0 +1,212 @@
+# Copy from https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/configuration_deepseek.py
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+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.
+
+
+    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,
+        )

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "eos_token_id": 163586,
+  "max_length": 262144,
+  "transformers_version": "4.57.1"
+}

model-00004-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a2ccbb19c35396788185385012a1a79e57edb81166ed42401cbaede98832b1
+size 4994959584

model-00011-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9199c784a8263238f7e1552f6c8ddc48113cb344bc2958b571eb3eb42d3b24f
+size 4994959064

model-00013-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72adee2fb15d766998bea53f5865b1bf194eceb7e215ee3e9f01f31f1f07b3cc
+size 4994959584

model-00017-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d4589a8ae3a687b6eee383438833fc5b906ba334b68da0cb39a4d2e4d515f6
+size 4994959592

model-00022-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa57599eb57c58a077b155fb7c48f13f8530f6f8641529a696b84e017b617c96
+size 4994959584

model-00034-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e3233c646fe4818ef9b0af6528e17b3676eec26c8d9b2eaf6c506d4005caa3
+size 4973857008

model-00035-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:769b2640f536857a97ab5f88378697e374a6579c9d28a58351b33ad83e14ad5b
+size 4994959592

model-00037-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a13d0cba926ca6ecd797c1c72750e6d56061a4ae0c931bdd84afa3b15fecffe
+size 4973856480

model-00056-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22268c3f70f7c11d3f2773b0d7c41119cf4175f5c4a3fbaaae6467a7aa564d01
+size 4994959336

model-00299-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04da0f9f667c0fdab07172c21ba829a4b180f42e8e0e15739800cde268efbf89
+size 4998136688

model-00316-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c02bf2103a9a1e7449f5a4fdf4b1b37203aae533e069c8fc3015a6feb895f3
+size 4998136960

model-00325-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e222ccf03a4c35b3f1ef6b4e1e7a66eaf2d45d5e58a8a131bcdaffef8cdb91ac
+size 4998136824

model-00401-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a585b6f12b09c74e4e61fbd6e5792bd23279ce768969bfff512581715cde21
+size 4994960120

model-00415-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b883b30c3277edaa13ddd57ab2b87ecb292594da45ae40f91ef52c63f4c1e14b
+size 4973857384

model-00418-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75598b1a2768da67a56d8fdd97aa297cb8203980ab8e3e302519667a0577bcea
+size 4994960120

model-00424-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5817b674961c123b05261ae415bf96b57f5e3b9a24d61d579d5cfe2e6877884f
+size 4973857512

model-00430-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2c0bf7c02a9d0acc8ccb7b4d5989afb228953c7e7a3da1167ff8f773baf5c8
+size 4998136840

model-00431-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a71a4cedb1ab7eb7edd6e33b84c5cb35d828f371879197825212bf7870b7e2e
+size 4973857008

model-00433-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4181c86ff9950975e398d538d0c9c6636a49e4ab0c54eb1879d918fcf9480f46
+size 4973857536

model-00434-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5fd465d5f788af68f9d7ea26da9e2e1c3254e5c99b2cd16a57c09996c37f42d
+size 4994960120

model-00435-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24de4225c7c30e6310b575fcd9abb15a3edbee4e65e3015e51c5f0c395afc2fb
+size 4973857536

model-00447-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d5979f434c155a425b90c72b3ffdf1281206ac7d127b85e76a45f394a51dc4
+size 4997875224

model-00453-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1410cc38f41af4f76528cfb0894e769ac2417c8078275fd4a9c99531a66a00a1
+size 4973857536

model-00454-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4b0959f7da1232a3974f4bc532559fc0612ba77be3fcfc2a247a069258a8f8
+size 4994960120

model-00456-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71b5318ea1067da5e6d63202c1a2202e73d2e29b7c1bdcad5c8bed02ce0f69b
+size 4998136968

model-00463-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbbb79782256ff6a87725f2192f1b1a10cb44ca917421204351dd2c001dad26
+size 4994960120

model-00468-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ba42b4ebaa61263b33b4884b78e95940596da12e4c008653f7d14c2cb2c698
+size 4994960120

model-00471-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f8a2fac8b4128330e754bb4fd7d0ecd76bf06771f8c8cbd97c9bef3fc5499a
+size 4973857536

model-00478-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d358e0f545d8c1450443cbc8a0a4098bf419de5fcdb3a459941d504439248ec
+size 4973857536

model-00482-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911d02c80774f402df76f6e9abc7bebbfa558ac50ede2891934e762b8471befd
+size 4968384168

model-00483-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c11949d4f1ddaa72d94cfc371b1048c04a7f923f8f5decda43bab458f4f8bc
+size 4995352144

model-00484-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5098ecc16ce1c552ed0c3cd3466e27e5af9b7a4856a8684ec832b0224722d596
+size 4973857008

model-00487-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97b3b6b247af852a78f69da49fe9d58a34bcb8d23c8b49d983c682bfbb94122
+size 4994960120

model-00491-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf50ec699cd37e83de75572e2053781b2c8a1af697c372da3e7dd92e1053e106
+size 4998136984

model-00497-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4961b8f150a0dd5ce6ffc95ce8920108994a0cefd0a1177c840c8ded2562a0b
+size 4973857536

model-00498-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19908ac72121b66c3a8004aa292145f325262c658592ed6442cb6f4c69bf01e
+size 4994960120

model-00499-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea787809ae7e4a1e1ba191afbfedbf7785b21e29a717d159ee02a3096c0172e
+size 4973857536

model-00518-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79bbcd2fc296bfb1de9031b3ef91df85817ef5e359e992694daf0f3360402ec0
+size 4988015168

model-00519-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2cf7316ab4e2a321e0d17df91efd9d71b67c3999ec76709c45c4adb11a6af8b
+size 4994959584

model-00520-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbcc4f14f9c76c8e002ca82fd603685170d227c07ec34b595185dab015661b93
+size 4973857376

model-00521-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1404c9149374fa03a62861f7b76cde5e39d7e9510c9990779637fa620522646
+size 4994960120

model-00522-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294685791ba67962720d0e03bf3ade07fc59568e0e98273329bb4138467d3de5
+size 4973857536

model-00527-of-00527.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf8d385a433c11531088dbf7f22ac16b71fc2366659d0a4d544d2a9ddb758bef
+size 2348810368

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "[EOT]",
+    "<|im_system|>",
+    "<|im_middle|>"
+  ],
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenization_kimi.py

@@ -0,0 +1,349 @@
+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, pre_tokenizers, Regex
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
+from typing import Any
+
+
+logger = getLogger(__name__)
+VOCAB_FILES_NAMES = {"vocab_file": "tiktoken.model"}
+
+
+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, None]=None,
+        pad_token: Union[str, AddedToken, None]=None,
+        additional_special_tokens: 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_user|>", 
+                "<|im_assistant|>", 
+                "<|start_header_id|>", 
+                "<|end_header_id|>", 
+                "[EOT]", 
+                "<|im_system|>", 
+                "<|im_middle|>",
+            ] 
+        
+        special_tokens_mapping = {
+        i: added_tokens_decoder[i].content for i in added_tokens_decoder
+    }
+
+        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,
+            added_tokens_decoder=added_tokens_decoder,
+            **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.
+        # NOTE: our encode method is not compatible with the super().encode method,
+        #   e.g. split_special_tokens' default is True in our encode method.
+        if len(kwargs) > 0:
+            logger.warning( f"Calling super().encode with {kwargs}" )
+            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
+
+        texts = self.pre_tokenizer_process(text)
+
+        all_substrs = []
+        for text in texts:
+            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
+                )
+            )
+            all_substrs.extend(substrs)
+
+        t: List[int] = []
+        for substr in all_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:
+            token_ids (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)
+
+        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:]
+
+    def pre_tokenizer_process(self, text: str) -> List[str]:
+        """
+        pre-tokenizes the input text into a list of tokens.
+        This method is used to split the input text into smaller chunks for internal processing.
+        """
+        return [text]
+
+
+    """ ----- 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)
+        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):
+            raise ValueError(f"vocabulary path ({save_directory}) should be a directory")
+        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,)
+    
+
+    
+    def apply_chat_template(
+        self, conversation, tools: Optional[list[dict]] = None, 
+        tokenize: bool = False, 
+        add_generation_prompt: bool = True, 
+        **kwargs
+    ):
+        tools = deep_sort_dict(tools)
+        return super().apply_chat_template(conversation, 
+                                           tools=tools,
+                                           tokenize=tokenize,
+                                           add_generation_prompt=add_generation_prompt, 
+                                           **kwargs)
+    
+
+def deep_sort_dict(obj: Any) -> Any:
+    if isinstance(obj, dict):
+        return {k: deep_sort_dict(v) for k, v in sorted(obj.items())}
+    if isinstance(obj, list):
+        return [deep_sort_dict(item) for item in obj]
+    return obj
+

tokenizer_config.json

@@ -0,0 +1,180 @@
+{
+  "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
+    },
+    "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
+    },
+    "163590": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163591": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163593": {
+      "content": "[EOT]",
+      "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
+    },
+    "163595": {
+      "content": "<|tool_calls_section_begin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163596": {
+      "content": "<|tool_calls_section_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163597": {
+      "content": "<|tool_call_begin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163598": {
+      "content": "<|tool_call_argument_begin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163599": {
+      "content": "<|tool_call_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163601": {
+      "content": "<|im_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163606": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163607": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163838": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163839": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "[EOT]",
+    "<|im_system|>",
+    "<|im_middle|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_kimi.TikTokenTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TikTokenTokenizer",
+  "unk_token": "[UNK]"
+}