add ckpts and artifacts

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 +1,219 @@
+{
+    "_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,
+    "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,
+    "quantization_config": {
+        "config_groups": {
+            "group_0": {
+                "input_activations": {
+                    "dynamic": false,
+                    "num_bits": 4,
+                    "type": "float",
+                    "group_size": 16
+                },
+                "weights": {
+                    "dynamic": false,
+                    "num_bits": 4,
+                    "type": "float",
+                    "group_size": 16
+                },
+                "targets": [
+                    "Linear"
+                ]
+            }
+        },
+        "ignore": [
+            "lm_head",
+            "model.layers.0*",
+            "model.layers.1.mlp.shared_experts*",
+            "model.layers.1.self_attn*",
+            "model.layers.10.mlp.shared_experts*",
+            "model.layers.10.self_attn*",
+            "model.layers.11.mlp.shared_experts*",
+            "model.layers.11.self_attn*",
+            "model.layers.12.mlp.shared_experts*",
+            "model.layers.12.self_attn*",
+            "model.layers.13.mlp.shared_experts*",
+            "model.layers.13.self_attn*",
+            "model.layers.14.mlp.shared_experts*",
+            "model.layers.14.self_attn*",
+            "model.layers.15.mlp.shared_experts*",
+            "model.layers.15.self_attn*",
+            "model.layers.16.mlp.shared_experts*",
+            "model.layers.16.self_attn*",
+            "model.layers.17.mlp.shared_experts*",
+            "model.layers.17.self_attn*",
+            "model.layers.18.mlp.shared_experts*",
+            "model.layers.18.self_attn*",
+            "model.layers.19.mlp.shared_experts*",
+            "model.layers.19.self_attn*",
+            "model.layers.2.mlp.shared_experts*",
+            "model.layers.2.self_attn*",
+            "model.layers.20.mlp.shared_experts*",
+            "model.layers.20.self_attn*",
+            "model.layers.21.mlp.shared_experts*",
+            "model.layers.21.self_attn*",
+            "model.layers.22.mlp.shared_experts*",
+            "model.layers.22.self_attn*",
+            "model.layers.23.mlp.shared_experts*",
+            "model.layers.23.self_attn*",
+            "model.layers.24.mlp.shared_experts*",
+            "model.layers.24.self_attn*",
+            "model.layers.25.mlp.shared_experts*",
+            "model.layers.25.self_attn*",
+            "model.layers.26.mlp.shared_experts*",
+            "model.layers.26.self_attn*",
+            "model.layers.27.mlp.shared_experts*",
+            "model.layers.27.self_attn*",
+            "model.layers.28.mlp.shared_experts*",
+            "model.layers.28.self_attn*",
+            "model.layers.29.mlp.shared_experts*",
+            "model.layers.29.self_attn*",
+            "model.layers.3.mlp.shared_experts*",
+            "model.layers.3.self_attn*",
+            "model.layers.30.mlp.shared_experts*",
+            "model.layers.30.self_attn*",
+            "model.layers.31.mlp.shared_experts*",
+            "model.layers.31.self_attn*",
+            "model.layers.32.mlp.shared_experts*",
+            "model.layers.32.self_attn*",
+            "model.layers.33.mlp.shared_experts*",
+            "model.layers.33.self_attn*",
+            "model.layers.34.mlp.shared_experts*",
+            "model.layers.34.self_attn*",
+            "model.layers.35.mlp.shared_experts*",
+            "model.layers.35.self_attn*",
+            "model.layers.36.mlp.shared_experts*",
+            "model.layers.36.self_attn*",
+            "model.layers.37.mlp.shared_experts*",
+            "model.layers.37.self_attn*",
+            "model.layers.38.mlp.shared_experts*",
+            "model.layers.38.self_attn*",
+            "model.layers.39.mlp.shared_experts*",
+            "model.layers.39.self_attn*",
+            "model.layers.4.mlp.shared_experts*",
+            "model.layers.4.self_attn*",
+            "model.layers.40.mlp.shared_experts*",
+            "model.layers.40.self_attn*",
+            "model.layers.41.mlp.shared_experts*",
+            "model.layers.41.self_attn*",
+            "model.layers.42.mlp.shared_experts*",
+            "model.layers.42.self_attn*",
+            "model.layers.43.mlp.shared_experts*",
+            "model.layers.43.self_attn*",
+            "model.layers.44.mlp.shared_experts*",
+            "model.layers.44.self_attn*",
+            "model.layers.45.mlp.shared_experts*",
+            "model.layers.45.self_attn*",
+            "model.layers.46.mlp.shared_experts*",
+            "model.layers.46.self_attn*",
+            "model.layers.47.mlp.shared_experts*",
+            "model.layers.47.self_attn*",
+            "model.layers.48.mlp.shared_experts*",
+            "model.layers.48.self_attn*",
+            "model.layers.49.mlp.shared_experts*",
+            "model.layers.49.self_attn*",
+            "model.layers.5.mlp.shared_experts*",
+            "model.layers.5.self_attn*",
+            "model.layers.50.mlp.shared_experts*",
+            "model.layers.50.self_attn*",
+            "model.layers.51.mlp.shared_experts*",
+            "model.layers.51.self_attn*",
+            "model.layers.52.mlp.shared_experts*",
+            "model.layers.52.self_attn*",
+            "model.layers.53.mlp.shared_experts*",
+            "model.layers.53.self_attn*",
+            "model.layers.54.mlp.shared_experts*",
+            "model.layers.54.self_attn*",
+            "model.layers.55.mlp.shared_experts*",
+            "model.layers.55.self_attn*",
+            "model.layers.56.mlp.shared_experts*",
+            "model.layers.56.self_attn*",
+            "model.layers.57.mlp.shared_experts*",
+            "model.layers.57.self_attn*",
+            "model.layers.58.mlp.shared_experts*",
+            "model.layers.58.self_attn*",
+            "model.layers.59.mlp.shared_experts*",
+            "model.layers.59.self_attn*",
+            "model.layers.6.mlp.shared_experts*",
+            "model.layers.6.self_attn*",
+            "model.layers.60.mlp.shared_experts*",
+            "model.layers.60.self_attn*",
+            "model.layers.7.mlp.shared_experts*",
+            "model.layers.7.self_attn*",
+            "model.layers.8.mlp.shared_experts*",
+            "model.layers.8.self_attn*",
+            "model.layers.9.mlp.shared_experts*",
+            "model.layers.9.self_attn*"
+        ],
+        "quant_algo": "NVFP4",
+        "kv_cache_scheme": {
+            "dynamic": false,
+            "num_bits": 8,
+            "type": "float"
+        },
+        "producer": {
+            "name": "modelopt",
+            "version": "0.40.0.dev66+gbe64f6b1d.d20251119"
+        },
+        "quant_method": "modelopt"
+    }
+}

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"
+}

hf_quant_config.json

@@ -0,0 +1,135 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.40.0.dev66+gbe64f6b1d.d20251119"
+    },
+    "quantization": {
+        "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": "FP8",
+        "group_size": 16,
+        "exclude_modules": [
+            "lm_head",
+            "model.layers.0*",
+            "model.layers.1.mlp.shared_experts*",
+            "model.layers.1.self_attn*",
+            "model.layers.10.mlp.shared_experts*",
+            "model.layers.10.self_attn*",
+            "model.layers.11.mlp.shared_experts*",
+            "model.layers.11.self_attn*",
+            "model.layers.12.mlp.shared_experts*",
+            "model.layers.12.self_attn*",
+            "model.layers.13.mlp.shared_experts*",
+            "model.layers.13.self_attn*",
+            "model.layers.14.mlp.shared_experts*",
+            "model.layers.14.self_attn*",
+            "model.layers.15.mlp.shared_experts*",
+            "model.layers.15.self_attn*",
+            "model.layers.16.mlp.shared_experts*",
+            "model.layers.16.self_attn*",
+            "model.layers.17.mlp.shared_experts*",
+            "model.layers.17.self_attn*",
+            "model.layers.18.mlp.shared_experts*",
+            "model.layers.18.self_attn*",
+            "model.layers.19.mlp.shared_experts*",
+            "model.layers.19.self_attn*",
+            "model.layers.2.mlp.shared_experts*",
+            "model.layers.2.self_attn*",
+            "model.layers.20.mlp.shared_experts*",
+            "model.layers.20.self_attn*",
+            "model.layers.21.mlp.shared_experts*",
+            "model.layers.21.self_attn*",
+            "model.layers.22.mlp.shared_experts*",
+            "model.layers.22.self_attn*",
+            "model.layers.23.mlp.shared_experts*",
+            "model.layers.23.self_attn*",
+            "model.layers.24.mlp.shared_experts*",
+            "model.layers.24.self_attn*",
+            "model.layers.25.mlp.shared_experts*",
+            "model.layers.25.self_attn*",
+            "model.layers.26.mlp.shared_experts*",
+            "model.layers.26.self_attn*",
+            "model.layers.27.mlp.shared_experts*",
+            "model.layers.27.self_attn*",
+            "model.layers.28.mlp.shared_experts*",
+            "model.layers.28.self_attn*",
+            "model.layers.29.mlp.shared_experts*",
+            "model.layers.29.self_attn*",
+            "model.layers.3.mlp.shared_experts*",
+            "model.layers.3.self_attn*",
+            "model.layers.30.mlp.shared_experts*",
+            "model.layers.30.self_attn*",
+            "model.layers.31.mlp.shared_experts*",
+            "model.layers.31.self_attn*",
+            "model.layers.32.mlp.shared_experts*",
+            "model.layers.32.self_attn*",
+            "model.layers.33.mlp.shared_experts*",
+            "model.layers.33.self_attn*",
+            "model.layers.34.mlp.shared_experts*",
+            "model.layers.34.self_attn*",
+            "model.layers.35.mlp.shared_experts*",
+            "model.layers.35.self_attn*",
+            "model.layers.36.mlp.shared_experts*",
+            "model.layers.36.self_attn*",
+            "model.layers.37.mlp.shared_experts*",
+            "model.layers.37.self_attn*",
+            "model.layers.38.mlp.shared_experts*",
+            "model.layers.38.self_attn*",
+            "model.layers.39.mlp.shared_experts*",
+            "model.layers.39.self_attn*",
+            "model.layers.4.mlp.shared_experts*",
+            "model.layers.4.self_attn*",
+            "model.layers.40.mlp.shared_experts*",
+            "model.layers.40.self_attn*",
+            "model.layers.41.mlp.shared_experts*",
+            "model.layers.41.self_attn*",
+            "model.layers.42.mlp.shared_experts*",
+            "model.layers.42.self_attn*",
+            "model.layers.43.mlp.shared_experts*",
+            "model.layers.43.self_attn*",
+            "model.layers.44.mlp.shared_experts*",
+            "model.layers.44.self_attn*",
+            "model.layers.45.mlp.shared_experts*",
+            "model.layers.45.self_attn*",
+            "model.layers.46.mlp.shared_experts*",
+            "model.layers.46.self_attn*",
+            "model.layers.47.mlp.shared_experts*",
+            "model.layers.47.self_attn*",
+            "model.layers.48.mlp.shared_experts*",
+            "model.layers.48.self_attn*",
+            "model.layers.49.mlp.shared_experts*",
+            "model.layers.49.self_attn*",
+            "model.layers.5.mlp.shared_experts*",
+            "model.layers.5.self_attn*",
+            "model.layers.50.mlp.shared_experts*",
+            "model.layers.50.self_attn*",
+            "model.layers.51.mlp.shared_experts*",
+            "model.layers.51.self_attn*",
+            "model.layers.52.mlp.shared_experts*",
+            "model.layers.52.self_attn*",
+            "model.layers.53.mlp.shared_experts*",
+            "model.layers.53.self_attn*",
+            "model.layers.54.mlp.shared_experts*",
+            "model.layers.54.self_attn*",
+            "model.layers.55.mlp.shared_experts*",
+            "model.layers.55.self_attn*",
+            "model.layers.56.mlp.shared_experts*",
+            "model.layers.56.self_attn*",
+            "model.layers.57.mlp.shared_experts*",
+            "model.layers.57.self_attn*",
+            "model.layers.58.mlp.shared_experts*",
+            "model.layers.58.self_attn*",
+            "model.layers.59.mlp.shared_experts*",
+            "model.layers.59.self_attn*",
+            "model.layers.6.mlp.shared_experts*",
+            "model.layers.6.self_attn*",
+            "model.layers.60.mlp.shared_experts*",
+            "model.layers.60.self_attn*",
+            "model.layers.7.mlp.shared_experts*",
+            "model.layers.7.self_attn*",
+            "model.layers.8.mlp.shared_experts*",
+            "model.layers.8.self_attn*",
+            "model.layers.9.mlp.shared_experts*",
+            "model.layers.9.self_attn*"
+        ]
+    }
+}

model-00001-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0065c2ded569519c0b800245c7ac5dabbee794c660c19fb0434c246f8c89af39
+size 4999471752

model-00002-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c898b8b06b51a18c9eac7d3d34cbdc419f15be07a8c8d09d3ffe5c5c4af5c5b3
+size 4996099728

model-00003-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1789d63d20f95e791730a3164491cc9c9a9d88cf319839c69a57a6caad7c4961
+size 4994675824

model-00004-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c566d943a52889b51ad80ab3b51450b004d2821d57b0d75c1a76597c94ae68
+size 4996099808

model-00005-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e620c071a2ff20ddbb0fb5102c788a0a9319386ef69088f5f3689cbdc5f8784
+size 4994675744

model-00006-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1848b2b37a91dbe73f6517737367c767e6c744ba6ce5fbdd7400da88a295386
+size 4996099896

model-00007-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1709bd5d9a85e059dbdf9e853292bab3dbae83620dbf959f80f7792829ccc49d
+size 4994675648

model-00008-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ae1ec90815c73326255692c749336d8e2445cd59b0a686314bb156656e5277
+size 4996099992

model-00009-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d982ef0577772766bdef2850ab7897aef49847e64f44d75510b4da89a518a8
+size 4994675560

model-00010-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594cb42695e282b92a6617a0725be7419fc29b5feed74669548928f3bc059b06
+size 4996100072

model-00011-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69930f460407d09827005794ef32f1dbc3b410397113b6c0405fb7b564221127
+size 4994675480

model-00012-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260a8b9d974591b59ff64677d1c96249bf3c596f7ed6997b6cb1950b14be7990
+size 4996100160

model-00013-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0fb566f566874f46e820c4b02c46c3e3b8aa6429f3ef57de97190a992e43b6
+size 4994675416

model-00014-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75879f08917a21bf874be5c896ff21bbc8239650ba71cf185eba154a283b9141
+size 4996100224

model-00015-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c21ba4702a91ef74105d8af0b55f50987787839d2b11680a6caa05424cca1d
+size 4994675416

model-00016-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef51064876412b2482e4cbecc2109f75cb25eba16f25501c0813d0a95005dcdd
+size 4996100216

model-00017-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4e7964f19818e294e2ea1ed6e445a7751120f9daf48ff41a33253a4616d51d
+size 4994675424

model-00018-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f211a299d7e5b2ea3d327954d6d1e6cd5012bf88a51b08dbb7965250275e70c
+size 4996100216

model-00019-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d907c7ad5312354dfd2d477c936638b62881723efd32249108bafaf77feaad
+size 4994676936

model-00020-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40375f900fac3e70c84e69639e0a1fe479a8c6fa218231bba663cf5a94fdbfe6
+size 4996102640

model-00021-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba303a440792ab37a51151e485887608b90567390a00026cfd47e3282645839
+size 4994677704

model-00022-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c89f011829c7d575599e1ce55016d897cb8cb856ae4fcdc835980dfad9d64d
+size 4996102632

model-00023-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2ef499a7a739075c70781ca5cbfc162b7670290fcf1326b574a6332aac12e9
+size 4994677712

model-00024-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83ce76babcce707e80be70f9d2b9a2da8062427e53150ef206663b061764fa5
+size 4996102632

model-00025-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa89edd59ed5045f912860890c6b7db34c2e48d0ff20dd366aa64899b80ef9d
+size 4994677704

model-00026-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935b66202811d8c575209f45ee726f46ec8758c5a252305e49835896bb958a77
+size 4996102640

model-00027-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312bac8c5f3e45a31ed8c11bbbd2715099e60ae5a477928ead04aff1d24d3def
+size 4994677704

model-00028-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3679dc57662dbf5f4d5e2874c4fffe2474642e810de7630c0baf4152a0ab6341
+size 4996102632

model-00029-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2ef7b6edfb64c5ef3b831831a2efe5a1ae52ffdd9c5c1e45e2f539a2a0d388
+size 4994677712

model-00030-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a2043916fce2cf824b2e4551fb5833ed95b3ec323f62ae9a98c921ddb1876b
+size 4996102632

model-00031-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312da86b41f1070e56f6e233a5572db67c8e509781e1307dd39fe93cc2a201d9
+size 4994677704

model-00032-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf310f065b50c64a51f4938113aa5c831ff9a15ea52a77f1ae7be6809285510d
+size 4996102640

model-00033-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ceeeddb974a738246a07949d1155b4882adec914a252196473ce326b9f68b8f
+size 4994677704

model-00034-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b4d2c3ec16ffa2ad884728fdd57dbed149ca5354920ac365b604716045125c
+size 4996102632

model-00035-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349e755fd0f37ae43af44a36f116ce523c4db512e290f2e84c46153864c25b7f
+size 4994677712

model-00036-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2f8944925eadd3ae5b6053f9446cdc63d6d87f047818967700eecb0dc36a50
+size 4976834600

model-00037-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ff24de45eb025b8602c08fc74fda6be3ee3f73d293ae239e4c2e3136e13e54
+size 4997429720

model-00038-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad91ed25976754a7d159a8f5c32715023215e5d3e722b84bc5ea3cd00b0c5c0
+size 4984592456

model-00039-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc7524fe27ba7b8ca433514875c444af83005f30d8e568d91f9935e2be722c2
+size 4997930104

model-00040-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2820f62e17e5dd6ed35271c60c982f72ac89982eeed8eef71dfde65002d9584
+size 4994678960

model-00041-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e9f8c97a65a0569802ac3b70e0e6a51e6733afc7b1a6e1bf349ea22e669af5
+size 4996101384

model-00042-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50ea606d235edd493f59a5bf321027394c85961503ad1e95982661deb52a4fe
+size 4994678784

model-00043-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591c7db751c65f6f0ac16f647f853ac2a3c465b4acae4a2252aacf349a581fc8
+size 4996101552

model-00044-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8dc5a5befdc2b24c2789d6b9f26144a121bed72d664245419f86fa9be014a1
+size 4994678704

model-00045-of-00119.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2901a319bb4ae7755b03cde6c3a196ffc04cedd02d8a25dc53cb10ba337ae762
+size 4996101640