feat(phase-04): Wyoming Satellite integration + OpenClaw HA components

## Voice Pipeline (P3) - Replace openWakeWord daemon with Wyoming Satellite approach - Add Wyoming Satellite service on port 10700 for HA voice pipeline - Update setup.sh with cross-platform sed compatibility (macOS/Linux) - Add version field to Kokoro TTS voice info - Update launchd service loader to use Wyoming Satellite ## Home Assistant Integration (P4) - Add custom conversation agent component (openclaw_conversation) - Fix: Use IntentResponse instead of plain strings (HA API requirement) - Support both HTTP API and CLI fallback modes - Config flow for easy HA UI setup - Add OpenClaw bridge scripts (Python + Bash) - Add ha-ctl utility for HA entity control - Fix: Use context manager for token file reading - Add HA configuration examples and documentation ## Infrastructure - Add mem0 backup automation (launchd + script) - Add n8n workflow templates (morning briefing, notification router) - Add VS Code workspace configuration - Reorganize model files into categorized folders: - lmstudio-community/ - mlx-community/ - bartowski/ - mradermacher/ ## Documentation - Update PROJECT_PLAN.md with Wyoming Satellite architecture - Update TODO.md with completed Wyoming integration tasks - Add OPENCLAW_INTEGRATION.md for HA setup guide ## Testing - Verified Wyoming services running (STT:10300, TTS:10301, Satellite:10700) - Verified OpenClaw CLI accessibility - Confirmed cross-platform compatibility fixes
2026-03-08 02:06:37 +00:00
parent 9eb5633115
commit 6a0bae2a0b
119 changed files with 780808 additions and 64 deletions
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/config.json
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/config.json
@@ -0,0 +1,63 @@
+{
+    "architectures": [
+        "DeepseekV2ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_deepseek.DeepseekV2Config",
+        "AutoModel": "modeling_deepseek.DeepseekV2Model",
+        "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
+    },
+    "aux_loss_alpha": 0.001,
+    "bos_token_id": 100000,
+    "eos_token_id": 100001,
+    "first_k_dense_replace": 1,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 10944,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 163840,
+    "model_type": "deepseek_v2",
+    "moe_intermediate_size": 1408,
+    "moe_layer_freq": 1,
+    "n_group": 1,
+    "n_routed_experts": 64,
+    "n_shared_experts": 2,
+    "norm_topk_prob": false,
+    "num_attention_heads": 16,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "pretraining_tp": 1,
+    "q_lora_rank": null,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "beta_fast": 32,
+        "beta_slow": 1,
+        "factor": 40,
+        "mscale": 0.707,
+        "mscale_all_dim": 0.707,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 10000,
+    "routed_scaling_factor": 1.0,
+    "scoring_func": "softmax",
+    "seq_aux": true,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "topk_method": "greedy",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.3",
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 102400
+}
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/configuration_deepseek.py
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/configuration_deepseek.py
@@ -0,0 +1,206 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV2Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV2Model`]. 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 [`DeepseekV2Model`]
+        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 DeepseekV2Model, DeepseekV2Config
+
+    >>> # Initializing a Deepseek-V2 style configuration
+    >>> configuration = DeepseekV2Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v2"
+    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,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        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,
+        **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.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,
+        )
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/model.safetensors.index.json
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/model.safetensors.index.json
@@ -0,0 +1,922 @@
+{
+    "metadata": {
+        "total_size": 8839977984
+    },
+    "weight_map": {
+        "lm_head.biases": "model-00002-of-00002.safetensors",
+        "lm_head.scales": "model-00002-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_b_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_b_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_b_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_b_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/modeling_deepseek.py
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/modeling_deepseek.py
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/special_tokens_map.json
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/tokenization_deepseek_fast.py
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/tokenization_deepseek_fast.py
@@ -0,0 +1,38 @@
+from typing import List, Optional, Union
+
+
+from transformers.models.llama import LlamaTokenizerFast
+
+
+class DeepseekTokenizerFast(LlamaTokenizerFast):
+
+    def convert_ids_to_tokens(
+        self, ids: Union[int, List[int]], skip_special_tokens: bool = False
+    ) -> Union[str, List[str]]:
+        """
+        Converts a single index or a sequence of indices in a token or a sequence of tokens, using the vocabulary and
+        added tokens.
+
+        Args:
+            ids (`int` or `List[int]`):
+                The token id (or token ids) to convert to tokens.
+            skip_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not to remove special tokens in the decoding.
+
+        Returns:
+            `str` or `List[str]`: The decoded token(s).
+        """
+        if isinstance(ids, int):
+            return self._convert_id_to_token(ids)
+        tokens = []
+        for index in ids:
+            index = int(index)
+            if skip_special_tokens and index in self.all_special_ids:
+                continue
+            token = self._tokenizer.id_to_token(index)
+            tokens.append(token if token is not None else "")
+        return tokens
+    
+    def _convert_id_to_token(self, index: int) -> Optional[str]:
+        token = self._tokenizer.id_to_token(int(index))
+        return token if token is not None else ""
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/tokenizer.json
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/tokenizer.json
--- a/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/tokenizer_config.json
+++ b/homeai-llm/modelfiles/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx/tokenizer_config.json
@@ -0,0 +1,162 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "<｜completion｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100009": {
+      "content": "<｜tool▁calls▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "<｜tool▁calls▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "<｜tool▁call▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "<｜tool▁call▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "<｜tool▁outputs▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "<｜tool▁outputs▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<｜tool▁output▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100016": {
+      "content": "<｜tool▁output▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100017": {
+      "content": "<｜tool▁sep｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}