Add files using upload-large-folder tool

added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</think>": 75873,
+  "</tool_call>": 75877,
+  "</tool_response>": 75879,
+  "</tools>": 75875,
+  "<CLS>": 75858,
+  "<EOD>": 75860,
+  "<MASK>": 75861,
+  "<PAD>": 75862,
+  "<SEP>": 75859,
+  "<think>": 75872,
+  "<tool_call>": 75876,
+  "<tool_response>": 75878,
+  "<tools>": 75874,
+  "<|CLS|>": 75880,
+  "<|EOD|>": 75882,
+  "<|MASK|>": 75883,
+  "<|PAD|>": 75884,
+  "<|SEP|>": 75881,
+  "<|endoftext|>": 75869,
+  "<|file_sep|>": 75871,
+  "<|fim_middle|>": 75866,
+  "<|fim_pad|>": 75868,
+  "<|fim_prefix|>": 75865,
+  "<|fim_suffix|>": 75867,
+  "<|im_end|>": 75864,
+  "<|im_start|>": 75863,
+  "<|repo_name|>": 75870
+}

chat_template.jinja

@@ -0,0 +1,100 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- else %}
+        {{- 'You are IndustrialCoder, a helpful assistant developed by Beihang University.' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.type == 'function' and tool.function %}
+            {%- set func = tool.function %}
+        {%- else %}
+            {%- set func = tool %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" + func.name + "</name>" }}
+        {%- if func.description %}
+            {{- "\n<description>" + func.description + "</description>" }}
+        {%- endif %}
+        {{- "\n<parameters>" }}
+        {%- if func.parameters and func.parameters.properties %}
+            {%- for param_name, param_fields in func.parameters.properties.items() %}
+                {{- "\n<parameter>" }}
+                {{- "\n<name>" + param_name + "</name>" }}
+                {%- if param_fields.type %}
+                    {{- "\n<type>" + param_fields.type + "</type>" }}
+                {%- endif %}
+                {%- if param_fields.description %}
+                    {{- "\n<description>" + param_fields.description + "</description>" }}
+                {%- endif %}
+                {{- "\n</parameter>" }}
+            {%- endfor %}
+        {%- endif %}
+        {{- "\n</parameters>\n</function>" }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nIf you choose to call a function ONLY reply in the following format:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n</function>\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are IndustrialCoder, a helpful assistant developed by Beihang University.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tc = tool_call.function %}
+                {%- else %}
+                    {%- set tc = tool_call %}
+                {%- endif %}
+                {{- '<tool_call>\n<function=' + tc.name + '>\n' }}
+                {%- if tc.arguments is string %}
+                    {%- set args = tc.arguments | fromjson %}
+                {%- else %}
+                    {%- set args = tc.arguments %}
+                {%- endif %}
+                {%- for arg_name, arg_value in args.items() %}
+                    {{- '<parameter=' + arg_name + '>\n' }}
+                    {%- if arg_value is string %}
+                        {{- arg_value }}
+                    {%- else %}
+                        {{- arg_value | tojson }}
+                    {%- endif %}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,70 @@
+{
+    "architectures": [
+        "IQuestCoderForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_iquestcoder.IQuestCoderConfig",
+        "AutoModel": "modeling_iquestcoder.IQuestCoderModel",
+        "AutoModelForCausalLM": "modeling_iquestcoder.IQuestCoderForCausalLM",
+        "AutoModelForQuestionAnswering": "modeling_iquestcoder.IQuestCoderForQuestionAnswering",
+        "AutoModelForSequenceClassification": "modeling_iquestcoder.IQuestCoderForSequenceClassification",
+        "AutoModelForTokenClassification": "modeling_iquestcoder.IQuestCoderForTokenClassification"
+    },
+    "bos_token_id": 1,
+    "clip_qkv": null,
+    "eos_token_id": [
+        2,
+        75864,
+        75869
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 27648,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 0,
+    "mlp_bias": false,
+    "model_type": "iquestcoder",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.52.0",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 76800,
+    "compression_config": {
+        "config_groups": {
+            "group_0": {
+                "targets": [
+                    "Linear"
+                ],
+                "input_activations": null,
+                "weights": {
+                    "dynamic": false,
+                    "group_size": 128,
+                    "num_bits": 4,
+                    "observer": "minmax",
+                    "observer_kwargs": {},
+                    "strategy": "group",
+                    "symmetric": true,
+                    "type": "int"
+                }
+            }
+        },
+        "format": "pack-quantized",
+        "ignore": [
+            "lm_head"
+        ],
+        "quant_method": "compressed-tensors"
+    }
+}

configuration_iquestcoder.py

@@ -0,0 +1,182 @@
+"""IQuestCoder model configuration."""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class IQuestCoderConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`IQuestCoderModel`]. It is used to instantiate
+    an IQuestCoder model according to the specified arguments, defining the model architecture.
+
+    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 76800):
+            Vocabulary size of the IQuestCoder model. Defines the number of different tokens that can be represented
+            by the `inputs_ids` passed when calling [`IQuestCoderModel`].
+        hidden_size (`int`, *optional*, defaults to 5120):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 27648):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 80):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 40):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*, defaults to 8):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention (GQA).
+            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).
+        head_dim (`int`, *optional*, defaults to 128):
+            The dimension of each attention head. If not specified, defaults to `hidden_size // 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 16384):
+            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-05):
+            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).
+        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.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings.
+        rope_theta (`float`, *optional*, defaults to 500000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Supports various RoPE scaling
+            types including "linear", "dynamic", "yarn", "longrope", etc.
+        attention_bias (`bool`, *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.
+        mlp_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
+        clip_qkv (`float`, *optional*):
+            If set, clip the query, key, and value tensors to this value. Borrowed from OLMo for training stability.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention. Borrowed from Qwen2.
+        sliding_window (`int`, *optional*):
+            The sliding window size. Only effective when `use_sliding_window=True`.
+        max_window_layers (`int`, *optional*, defaults to 0):
+            The number of layers that don't use sliding window attention. Borrowed from Qwen2.
+
+    Example:
+        ```python
+        >>> from configuration_iquestcoder import IQuestCoderConfig
+        >>> from modeling_iquestcoder import IQuestCoderModel
+
+        >>> # Initializing a IQuestCoder configuration
+        >>> configuration = IQuestCoderConfig()
+
+        >>> # Initializing a model from the configuration
+        >>> model = IQuestCoderModel(configuration)
+
+        >>> # Accessing the model configuration
+        >>> configuration = model.config
+        ```
+    """
+
+    model_type = "iquestcoder"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=76800,
+        hidden_size=5120,
+        intermediate_size=27648,
+        num_hidden_layers=80,
+        num_attention_heads=40,
+        num_key_value_heads=8,
+        head_dim=128,
+        hidden_act="silu",
+        max_position_embeddings=16384,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        tie_word_embeddings=False,
+        rope_theta=500000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        mlp_bias=False,
+        # IQuestCoder specific (borrowed from OLMo)
+        clip_qkv=None,
+        # IQuestCoder specific (borrowed from Qwen2)
+        use_sliding_window=False,
+        sliding_window=None,
+        max_window_layers=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.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.head_dim = head_dim
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        self.mlp_bias = mlp_bias
+        # IQuestCoder specific
+        self.clip_qkv = clip_qkv
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window
+        self.max_window_layers = max_window_layers
+
+        # Validate rope_scaling configuration
+        self._rope_scaling_validation()
+
+        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,
+        )
+
+    def _rope_scaling_validation(self):
+        """Validate the `rope_scaling` configuration."""
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) < 1:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with a minimum of one field, `type` or `rope_type`."
+            )
+        
+        rope_scaling_type = self.rope_scaling.get("type", None) or self.rope_scaling.get("rope_type", None)
+        if rope_scaling_type is None:
+            raise ValueError(
+                "`rope_scaling` must have a `type` or `rope_type` field."
+            )
+        
+        valid_rope_types = ["linear", "dynamic", "yarn", "longrope", "llama3"]
+        if rope_scaling_type not in valid_rope_types:
+            raise ValueError(
+                f"`rope_scaling`'s type field must be one of {valid_rope_types}, got {rope_scaling_type}"
+            )
+
+
+__all__ = ["IQuestCoderConfig"]
+

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    75864,
+    75869
+  ],
+  "transformers_version": "4.52.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecc1d9460e7cd917ee0cd842a2094600f1330b1d53c6d39711997cebdfbf951
+size 4987813296

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f62c8b1660488ecb98d63077dfef4e8657618c874cb0b72edc3024898efa4e
+size 4955706728

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075f0b283d3a5fd6723dfb1f43cd31c4dd91288a51cc204ebc985af85e7f2479
+size 4955706728

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a8fe89b3045b5ba0ce806f0fda2086f7c1b92a3c569803c2e3c8e91a46d50a
+size 2765480192

model.safetensors.index.json

@@ -0,0 +1,1034 @@
+{
+  "metadata": {
+    "total_size": 17664583680
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.42.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.43.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.44.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.45.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.46.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.47.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.48.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.49.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.50.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.50.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.50.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.50.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.51.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.51.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.52.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.52.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.53.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.53.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.54.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.54.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.55.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.55.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.56.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.56.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.56.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.56.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.56.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.56.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.56.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.56.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.57.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.57.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.57.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.57.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.58.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.58.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.59.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.59.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.60.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.60.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.60.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.60.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.61.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.61.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.62.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.62.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.63.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.63.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    "<|CLS|>",
+    "<|SEP|>",
+    "<|EOD|>",
+    "<|MASK|>",
+    "<|PAD|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|fim_pad|>",
+    "<|endoftext|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

tokenization_iquestcoder.py

@@ -0,0 +1,552 @@
+"""Tokenization classes for IQuestCoder."""
+
+import os
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import sentencepiece as spm
+
+from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
+
+PRETRAINED_VOCAB_FILES_MAP = {
+    "vocab_file": {},
+    "tokenizer_file": {},
+}
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}
+
+
+
+class IQuestCoderTokenizer(PreTrainedTokenizer):
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file,
+        unk_token="<unk>",
+        bos_token="<s>",
+        eos_token="</s>",
+        pad_token=None,
+        sp_model_kwargs: Optional[Dict[str, Any]] = None,
+        add_bos_token=True,
+        add_eos_token=False,
+        clean_up_tokenization_spaces=False,
+        add_prefix_space=False,
+        legacy=None,
+        use_default_system_prompt=False,
+        chat_template=None,
+        **kwargs,
+    ):
+        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
+        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
+        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
+        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
+        
+        # Legacy behavior handling
+        if legacy is None:
+            logger.warning_once(
+                f"You are using the default legacy behaviour of the {self.__class__.__name__}. This is"
+                " expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you."
+                " If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it"
+                " means, and thoroughly read the reason why this was added as explained in"
+                " https://github.com/huggingface/transformers/pull/24565"
+            )
+            legacy = True
+        
+        self.legacy = legacy
+        self.vocab_file = vocab_file
+        self.add_bos_token = add_bos_token
+        self.add_eos_token = add_eos_token
+        self.add_prefix_space = add_prefix_space
+        self.use_default_system_prompt = use_default_system_prompt
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(vocab_file)
+        
+
+        
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            add_bos_token=add_bos_token,
+            add_eos_token=add_eos_token,
+            sp_model_kwargs=self.sp_model_kwargs,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            add_prefix_space=add_prefix_space,
+            legacy=legacy,
+            use_default_system_prompt=use_default_system_prompt,
+            chat_template=chat_template,
+            **kwargs,
+        )
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        state["sp_model"] = None
+        return state
+
+    def __setstate__(self, d):
+        self.__dict__ = d
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(self.vocab_file)
+
+    @property
+    def vocab_size(self) -> int:
+        """Returns the vocabulary size."""
+        return self.sp_model.get_piece_size()
+
+    def get_vocab(self) -> Dict[str, int]:
+        """Returns the vocabulary as a dictionary of token to index."""
+        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def _tokenize(self, text: str) -> List[str]:
+        """
+        Tokenize a string.
+        
+        Args:
+            text (`str`): The text to tokenize.
+            
+        Returns:
+            `List[str]`: The list of tokens.
+        """
+        if self.add_prefix_space:
+            text = " " + text
+            
+        if self.legacy:
+            return self.sp_model.encode(text, out_type=str)
+        
+        # Non-legacy behavior: handle special tokens properly
+        return self.sp_model.encode(text, out_type=str)
+
+    def _convert_token_to_id(self, token: str) -> int:
+        """Converts a token (str) to an id using the vocab."""
+        return self.sp_model.piece_to_id(token)
+
+    def _convert_id_to_token(self, index: int) -> str:
+        """Converts an index (integer) to a token (str) using the vocab."""
+        token = self.sp_model.IdToPiece(index)
+        return token
+
+    def convert_tokens_to_string(self, tokens: List[str]) -> str:
+        """
+        Converts a sequence of tokens (strings) to a single string.
+        
+        This method handles special tokens separately to ensure they are not
+        decoded using the SentencePiece model.
+        
+        Args:
+            tokens (`List[str]`): The list of tokens to convert.
+            
+        Returns:
+            `str`: The decoded string.
+        """
+        current_sub_tokens = []
+        out_string = ""
+        prev_is_special = False
+        for i, token in enumerate(tokens):
+            # make sure that special tokens are not decoded using sentencepiece model
+            if token in self.all_special_tokens:
+                if not prev_is_special and i != 0:
+                    out_string += " "
+                out_string += self.sp_model.decode(current_sub_tokens) + token
+                prev_is_special = True
+                current_sub_tokens = []
+            else:
+                current_sub_tokens.append(token)
+                prev_is_special = False
+        out_string += self.sp_model.decode(current_sub_tokens)
+        return out_string
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        """
+        Save the vocabulary and special tokens file to a directory.
+        
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+            filename_prefix (`str`, *optional*):
+                An optional prefix to add to the named of the saved files.
+                
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "wb") as fi:
+                content_spiece_model = self.sp_model.serialized_model_proto()
+                fi.write(content_spiece_model)
+
+        return (out_vocab_file,)
+
+    def build_inputs_with_special_tokens(
+        self, 
+        token_ids_0: List[int], 
+        token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequences for sequence classification tasks by concatenating
+        and adding special tokens.
+        
+        An IQuestCoder sequence has the following format:
+        
+        - single sequence: `<s> X </s>` (if add_eos_token is True) or `<s> X` (default)
+        - pair of sequences: `<s> A </s> <s> B </s>` (if add_eos_token is True) or `<s> A <s> B` (default)
+        
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+                
+        Returns:
+            `List[int]`: List of input IDs with the appropriate special tokens.
+        """
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = bos_token_id + token_ids_0 + eos_token_id
+
+        if token_ids_1 is not None:
+            output = output + bos_token_id + token_ids_1 + eos_token_id
+
+        return output
+
+    def get_special_tokens_mask(
+        self, 
+        token_ids_0: List[int], 
+        token_ids_1: Optional[List[int]] = None, 
+        already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+        
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+                
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        bos_token_id = [1] if self.add_bos_token else []
+        eos_token_id = [1] if self.add_eos_token else []
+
+        if token_ids_1 is None:
+            return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
+        return (
+            bos_token_id
+            + ([0] * len(token_ids_0))
+            + eos_token_id
+            + bos_token_id
+            + ([0] * len(token_ids_1))
+            + eos_token_id
+        )
+
+    def create_token_type_ids_from_sequences(
+        self, 
+        token_ids_0: List[int], 
+        token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task.
+        
+        An IQuestCoder sequence pair mask has the following format:
+        
+        ```
+        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+        | first sequence    | second sequence |
+        ```
+        
+        If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).
+        
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+                
+        Returns:
+            `List[int]`: List of token type IDs according to the given sequence(s).
+        """
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
+
+        if token_ids_1 is not None:
+            output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
+
+        return output
+
+    @property
+    def default_chat_template(self) -> str:
+        """
+        Returns the default chat template for IQuestCoder.
+        
+        This template formats conversations with system, user, and assistant roles.
+        """
+        return DEFAULT_CHAT_TEMPLATE
+
+    def apply_chat_template(
+        self,
+        conversation: Union[List[Dict[str, str]], "Conversation"],
+        chat_template: Optional[str] = None,
+        add_generation_prompt: bool = False,
+        tokenize: bool = True,
+        padding: bool = False,
+        truncation: bool = False,
+        max_length: Optional[int] = None,
+        return_tensors: Optional[str] = None,
+        return_dict: bool = False,
+        **tokenizer_kwargs,
+    ):
+        """
+        Apply a chat template to format a conversation.
+        
+        Args:
+            conversation (`List[Dict[str, str]]` or `Conversation`):
+                A list of dicts with "role" and "content" keys, representing the conversation history.
+            chat_template (`str`, *optional*):
+                A Jinja template to use for formatting. If not provided, the tokenizer's default will be used.
+            add_generation_prompt (`bool`, *optional*, defaults to `False`):
+                Whether to add a generation prompt at the end for the assistant to continue.
+            tokenize (`bool`, *optional*, defaults to `True`):
+                Whether to tokenize the output. If `False`, returns a string.
+            padding (`bool`, *optional*, defaults to `False`):
+                Whether to pad sequences.
+            truncation (`bool`, *optional*, defaults to `False`):
+                Whether to truncate sequences.
+            max_length (`int`, *optional*):
+                Maximum length of the output.
+            return_tensors (`str`, *optional*):
+                The type of tensors to return ("pt", "tf", "np", or None).
+            return_dict (`bool`, *optional*, defaults to `False`):
+                Whether to return a dictionary with additional information.
+            **tokenizer_kwargs:
+                Additional keyword arguments passed to the tokenizer.
+                
+        Returns:
+            `Union[str, List[int], BatchEncoding]`: The formatted (and optionally tokenized) conversation.
+            
+        Example:
+            ```python
+            >>> tokenizer = IQuestCoderTokenizer.from_pretrained("path/to/model")
+            >>> conversation = [
+            ...     {"role": "system", "content": "You are a helpful assistant."},
+            ...     {"role": "user", "content": "Hello!"},
+            ...     {"role": "assistant", "content": "Hi there! How can I help you today?"},
+            ...     {"role": "user", "content": "What's the weather like?"},
+            ... ]
+            >>> tokenizer.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
+            '<|system|>\\nYou are a helpful assistant.\\n</|system|><|user|>\\nHello!\\n</|user|>...'
+            ```
+        """
+        # Use parent class implementation with our template
+        return super().apply_chat_template(
+            conversation,
+            chat_template=chat_template,
+            add_generation_prompt=add_generation_prompt,
+            tokenize=tokenize,
+            padding=padding,
+            truncation=truncation,
+            max_length=max_length,
+            return_tensors=return_tensors,
+            return_dict=return_dict,
+            **tokenizer_kwargs,
+        )
+
+
+# Try to import and create Fast tokenizer version
+try:
+    from transformers import PreTrainedTokenizerFast
+    from tokenizers import Tokenizer, decoders, models, normalizers, pre_tokenizers, processors
+    
+    class IQuestCoderTokenizerFast(PreTrainedTokenizerFast):
+        """
+        Construct a "fast" IQuestCoder tokenizer (backed by HuggingFace's *tokenizers* library).
+        
+        This is a fast implementation of [`IQuestCoderTokenizer`] using the 🤗 Tokenizers library.
+        
+        Args:
+            vocab_file (`str`, *optional*):
+                Path to the vocabulary file (SentencePiece model).
+            tokenizer_file (`str`, *optional*):
+                Path to a tokenizer JSON file.
+            unk_token (`str`, *optional*, defaults to `"<unk>"`):
+                The unknown token.
+            bos_token (`str`, *optional*, defaults to `"<s>"`):
+                The beginning of sequence token.
+            eos_token (`str`, *optional*, defaults to `"</s>"`):
+                The end of sequence token.
+            pad_token (`str`, *optional*):
+                The token used for padding.
+            add_bos_token (`bool`, *optional*, defaults to `True`):
+                Whether to add a BOS token at the start of sequences.
+            add_eos_token (`bool`, *optional*, defaults to `False`):
+                Whether to add an EOS token at the end of sequences.
+            add_prefix_space (`bool`, *optional*, defaults to `False`):
+                Whether to add an initial space to the input.
+            use_default_system_prompt (`bool`, *optional*, defaults to `False`):
+                Whether to use the default system prompt.
+            chat_template (`str`, *optional*):
+                A Jinja template for formatting conversations.
+                
+        Example:
+            ```python
+            >>> from tokenization_iquestcoder import IQuestCoderTokenizerFast
+            
+            >>> tokenizer = IQuestCoderTokenizerFast.from_pretrained("path/to/model")
+            >>> tokenizer.encode("Hello, world!")
+            [1, 15043, 29892, 3186, 29991]
+            ```
+        """
+        
+        vocab_files_names = VOCAB_FILES_NAMES
+        pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+        max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+        model_input_names = ["input_ids", "attention_mask"]
+        slow_tokenizer_class = IQuestCoderTokenizer
+        
+        def __init__(
+            self,
+            vocab_file=None,
+            tokenizer_file=None,
+            unk_token="<unk>",
+            bos_token="<s>",
+            eos_token="</s>",
+            pad_token=None,
+            add_bos_token=True,
+            add_eos_token=False,
+            add_prefix_space=False,
+            use_default_system_prompt=False,
+            chat_template=None,
+            **kwargs,
+        ):
+            self.add_bos_token = add_bos_token
+            self.add_eos_token = add_eos_token
+            self.add_prefix_space = add_prefix_space
+            self.use_default_system_prompt = use_default_system_prompt
+            
+            if chat_template is None:
+                chat_template = DEFAULT_CHAT_TEMPLATE
+            
+            super().__init__(
+                vocab_file=vocab_file,
+                tokenizer_file=tokenizer_file,
+                unk_token=unk_token,
+                bos_token=bos_token,
+                eos_token=eos_token,
+                pad_token=pad_token,
+                add_bos_token=add_bos_token,
+                add_eos_token=add_eos_token,
+                add_prefix_space=add_prefix_space,
+                use_default_system_prompt=use_default_system_prompt,
+                chat_template=chat_template,
+                **kwargs,
+            )
+        
+        @property
+        def can_save_slow_tokenizer(self) -> bool:
+            return os.path.isfile(self.vocab_file) if self.vocab_file else False
+        
+        @property
+        def default_chat_template(self) -> str:
+            """Returns the default chat template."""
+            return DEFAULT_CHAT_TEMPLATE
+        
+        def build_inputs_with_special_tokens(
+            self, 
+            token_ids_0: List[int], 
+            token_ids_1: Optional[List[int]] = None
+        ) -> List[int]:
+            """Build model inputs with special tokens."""
+            bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+            eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+            output = bos_token_id + token_ids_0 + eos_token_id
+
+            if token_ids_1 is not None:
+                output = output + bos_token_id + token_ids_1 + eos_token_id
+
+            return output
+        
+        def get_special_tokens_mask(
+            self, 
+            token_ids_0: List[int], 
+            token_ids_1: Optional[List[int]] = None, 
+            already_has_special_tokens: bool = False
+        ) -> List[int]:
+            """Retrieve special tokens mask."""
+            if already_has_special_tokens:
+                return super().get_special_tokens_mask(
+                    token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+                )
+
+            bos_token_id = [1] if self.add_bos_token else []
+            eos_token_id = [1] if self.add_eos_token else []
+
+            if token_ids_1 is None:
+                return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
+            return (
+                bos_token_id
+                + ([0] * len(token_ids_0))
+                + eos_token_id
+                + bos_token_id
+                + ([0] * len(token_ids_1))
+                + eos_token_id
+            )
+        
+        def create_token_type_ids_from_sequences(
+            self, 
+            token_ids_0: List[int], 
+            token_ids_1: Optional[List[int]] = None
+        ) -> List[int]:
+            """Create token type IDs from sequences."""
+            bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+            eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+            output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
+
+            if token_ids_1 is not None:
+                output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
+
+            return output
+
+except ImportError:
+    # tokenizers library not available, Fast tokenizer not supported
+    IQuestCoderTokenizerFast = None
+    logger.info(
+        "The `tokenizers` library is not installed. "
+        "IQuestCoderTokenizerFast will not be available. "
+        "Install it with `pip install tokenizers`."
+    )
+

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3be68e090a927f31e0e378d7599b15c206dd47e4a73933775a746cc9c1cd91
+size 1345108

tokenizer_config.json

@@ -0,0 +1,283 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "75858": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75859": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75860": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75861": {
+      "content": "<MASK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75862": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75863": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75864": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75865": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75866": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75867": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75868": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75869": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75870": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75871": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75872": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75873": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75874": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75875": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75876": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75877": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75878": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75879": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75880": {
+      "content": "<|CLS|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75881": {
+      "content": "<|SEP|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75882": {
+      "content": "<|EOD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75883": {
+      "content": "<|MASK|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75884": {
+      "content": "<|PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|CLS|>",
+    "<|SEP|>",
+    "<|EOD|>",
+    "<|MASK|>",
+    "<|PAD|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|fim_pad|>",
+    "<|endoftext|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_iquestcoder.IQuestCoderTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "IQuestCoderTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": false
+}