Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,127 @@
+{
+  "</think>": 219406,
+  "<think>": 219404,
+  "<|assistant|>": 219402,
+  "<|beginoftext|>": 219396,
+  "<|dummy_id_100|>": 219505,
+  "<|dummy_id_101|>": 219506,
+  "<|dummy_id_102|>": 219507,
+  "<|dummy_id_103|>": 219508,
+  "<|dummy_id_104|>": 219509,
+  "<|dummy_id_105|>": 219510,
+  "<|dummy_id_106|>": 219511,
+  "<|dummy_id_107|>": 219512,
+  "<|dummy_id_108|>": 219513,
+  "<|dummy_id_109|>": 219514,
+  "<|dummy_id_10|>": 219414,
+  "<|dummy_id_110|>": 219515,
+  "<|dummy_id_111|>": 219516,
+  "<|dummy_id_112|>": 219517,
+  "<|dummy_id_113|>": 219518,
+  "<|dummy_id_114|>": 219519,
+  "<|dummy_id_11|>": 219415,
+  "<|dummy_id_12|>": 219417,
+  "<|dummy_id_13|>": 219418,
+  "<|dummy_id_14|>": 219419,
+  "<|dummy_id_15|>": 219420,
+  "<|dummy_id_16|>": 219421,
+  "<|dummy_id_17|>": 219422,
+  "<|dummy_id_18|>": 219423,
+  "<|dummy_id_19|>": 219424,
+  "<|dummy_id_20|>": 219425,
+  "<|dummy_id_21|>": 219426,
+  "<|dummy_id_22|>": 219427,
+  "<|dummy_id_23|>": 219428,
+  "<|dummy_id_24|>": 219429,
+  "<|dummy_id_25|>": 219430,
+  "<|dummy_id_26|>": 219431,
+  "<|dummy_id_27|>": 219432,
+  "<|dummy_id_28|>": 219433,
+  "<|dummy_id_29|>": 219434,
+  "<|dummy_id_30|>": 219435,
+  "<|dummy_id_31|>": 219436,
+  "<|dummy_id_32|>": 219437,
+  "<|dummy_id_33|>": 219438,
+  "<|dummy_id_34|>": 219439,
+  "<|dummy_id_35|>": 219440,
+  "<|dummy_id_36|>": 219441,
+  "<|dummy_id_37|>": 219442,
+  "<|dummy_id_38|>": 219443,
+  "<|dummy_id_39|>": 219444,
+  "<|dummy_id_3|>": 219407,
+  "<|dummy_id_40|>": 219445,
+  "<|dummy_id_41|>": 219446,
+  "<|dummy_id_42|>": 219447,
+  "<|dummy_id_43|>": 219448,
+  "<|dummy_id_44|>": 219449,
+  "<|dummy_id_45|>": 219450,
+  "<|dummy_id_46|>": 219451,
+  "<|dummy_id_47|>": 219452,
+  "<|dummy_id_48|>": 219453,
+  "<|dummy_id_49|>": 219454,
+  "<|dummy_id_4|>": 219408,
+  "<|dummy_id_50|>": 219455,
+  "<|dummy_id_51|>": 219456,
+  "<|dummy_id_52|>": 219457,
+  "<|dummy_id_53|>": 219458,
+  "<|dummy_id_54|>": 219459,
+  "<|dummy_id_55|>": 219460,
+  "<|dummy_id_56|>": 219461,
+  "<|dummy_id_57|>": 219462,
+  "<|dummy_id_58|>": 219463,
+  "<|dummy_id_59|>": 219464,
+  "<|dummy_id_5|>": 219409,
+  "<|dummy_id_60|>": 219465,
+  "<|dummy_id_61|>": 219466,
+  "<|dummy_id_62|>": 219467,
+  "<|dummy_id_63|>": 219468,
+  "<|dummy_id_64|>": 219469,
+  "<|dummy_id_65|>": 219470,
+  "<|dummy_id_66|>": 219471,
+  "<|dummy_id_67|>": 219472,
+  "<|dummy_id_68|>": 219473,
+  "<|dummy_id_69|>": 219474,
+  "<|dummy_id_6|>": 219410,
+  "<|dummy_id_70|>": 219475,
+  "<|dummy_id_71|>": 219476,
+  "<|dummy_id_72|>": 219477,
+  "<|dummy_id_73|>": 219478,
+  "<|dummy_id_74|>": 219479,
+  "<|dummy_id_75|>": 219480,
+  "<|dummy_id_76|>": 219481,
+  "<|dummy_id_77|>": 219482,
+  "<|dummy_id_78|>": 219483,
+  "<|dummy_id_79|>": 219484,
+  "<|dummy_id_7|>": 219411,
+  "<|dummy_id_80|>": 219485,
+  "<|dummy_id_81|>": 219486,
+  "<|dummy_id_82|>": 219487,
+  "<|dummy_id_83|>": 219488,
+  "<|dummy_id_84|>": 219489,
+  "<|dummy_id_85|>": 219490,
+  "<|dummy_id_86|>": 219491,
+  "<|dummy_id_87|>": 219492,
+  "<|dummy_id_88|>": 219493,
+  "<|dummy_id_89|>": 219494,
+  "<|dummy_id_8|>": 219412,
+  "<|dummy_id_90|>": 219495,
+  "<|dummy_id_91|>": 219496,
+  "<|dummy_id_92|>": 219497,
+  "<|dummy_id_93|>": 219498,
+  "<|dummy_id_94|>": 219499,
+  "<|dummy_id_95|>": 219500,
+  "<|dummy_id_96|>": 219501,
+  "<|dummy_id_97|>": 219502,
+  "<|dummy_id_98|>": 219503,
+  "<|dummy_id_99|>": 219504,
+  "<|dummy_id_9|>": 219413,
+  "<|endofprompt|>": 219416,
+  "<|endoftext|>": 219395,
+  "<|endofturn|>": 219405,
+  "<|fim_middle|>": 219398,
+  "<|fim_prefix|>": 219397,
+  "<|fim_suffix|>": 219399,
+  "<|startofturn|>": 219403,
+  "<|system|>": 219400,
+  "<|user|>": 219401
+}

config.json

@@ -0,0 +1,89 @@
+{
+  "absolute_position_embedding": false,
+  "architectures": [
+    "MotifForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_motif.MotifConfig",
+    "AutoModelForCausalLM": "modeling_motif.MotifForCausalLM"
+  },
+  "bfloat16": true,
+  "bos_token_id": 219396,
+  "continual_training": false,
+  "decoder_split_layers": [],
+  "decontam_attn": false,
+  "dim_model_base": 2048,
+  "dim_model_base_attn": 128,
+  "dim_model_base_init": 2048,
+  "dim_model_base_lmh": 1,
+  "dim_model_base_logits": 2048,
+  "dim_model_base_lr": 256,
+  "down_proj_alpha": 0.15625,
+  "embed_tokens_alpha": null,
+  "encoder_split_layers": [],
+  "eos_token_id": 219395,
+  "first_expansion": false,
+  "fused_rope": true,
+  "gate_up_proj_alpha": 0.15625,
+  "hidden_act": "poly_norm",
+  "hidden_act_moe": null,
+  "hidden_size": 2048,
+  "hidden_states_shrink": 0.17677669529663687,
+  "init_scale_o": 1,
+  "initializer_range": 2e-05,
+  "input_layernorm_alpha": null,
+  "intermediate_size": 8192,
+  "k_proj_alpha": 0.15625,
+  "lm_head_alpha": null,
+  "loss_reduction": "mean",
+  "max_position_embeddings": 16384,
+  "max_window_layers": 28,
+  "mix_attn": false,
+  "model_type": "Motif",
+  "moe": false,
+  "moe_intermediate_size": null,
+  "moe_layer": false,
+  "muP": false,
+  "multi_token_heads": null,
+  "n_group": null,
+  "n_routed_experts": null,
+  "norm_alpha": null,
+  "norm_topk_prob": null,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 16,
+  "num_stages": false,
+  "o_proj_alpha": 0.15625,
+  "post_attention_layernorm_alpha": null,
+  "q_proj_alpha": 0.15625,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "routed_scaling_factor": null,
+  "scale_emb": 1,
+  "scoring_func": null,
+  "seq_aux": null,
+  "sliding_window": null,
+  "tensor_parallel": true,
+  "tie_word_embeddings": true,
+  "topk_group": null,
+  "topk_method": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_advanced_parallelization": true,
+  "use_bias": false,
+  "use_cache": false,
+  "use_emb_alpha": false,
+  "use_fused_mlp": null,
+  "use_moreh_attention": true,
+  "use_moreh_moe": false,
+  "use_mrope": false,
+  "use_norm_alpha": false,
+  "use_pipeline": false,
+  "use_qk_norm": false,
+  "use_sliding_window": false,
+  "v_proj_alpha": 0.15625,
+  "vocab_size": 219520,
+  "wesar_weights": false
+}

configuration_motif.py

@@ -0,0 +1,251 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.modeling_rope_utils import rope_config_validation
+from transformers.utils import logging
+from typing import Optional
+import math
+
+logger = logging.get_logger(__name__)
+
+
+class MotifConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`MotifModel`]. It is used to instantiate a
+    Motif model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of
+    Motif-102B [moreh/Motif-102B](https://huggingface.co/moreh/Motif-102B).
+
+    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 151936):
+            Vocabulary size of the Motif model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`MotifModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 22016):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 32):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
+        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 32768):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 28):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import MotifModel, MotifConfig
+
+    >>> # Initializing a Motif style configuration
+    >>> configuration = MotifConfig()
+
+    >>> # Initializing a model from the Motif-102B style configuration
+    >>> model = MotifModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "Motif"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=151936,
+        hidden_size=4096,
+        intermediate_size=22016,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        multi_token_heads: Optional[int] = None,
+        **kwargs,
+    ):
+        """
+        Arguments:
+            multi_token_heads: If not None, use multi-token heads as in the paper https://arxiv.org/pdf/2404.19737
+        """
+
+        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.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window if use_sliding_window else None
+        self.max_window_layers = max_window_layers
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_dropout = attention_dropout
+
+        ###kwargs
+
+        # some scale factors
+
+        self.scale_emb = getattr(kwargs, "scale_emb", 1)
+        self.init_scale_o = getattr(kwargs, "init_scale_o", 1)
+
+        # muparam
+        self.hidden_states_shrink = 1 / math.sqrt(num_hidden_layers)
+        self.dim_model_base = hidden_size
+        self.dim_model_base_attn  = (hidden_size // num_attention_heads)
+        self.dim_model_base_init = hidden_size
+        self.dim_model_base_lr = getattr(kwargs, "dim_model_base_lr", hidden_size//8)
+        self.dim_model_base_lmh = 1
+        self.dim_model_base_logits = hidden_size
+
+        self.muP = getattr(kwargs, "muP", False)
+        # proxy hidden size ( following YuLan-Mini )
+        # reparameterization(wesar_weights)
+        logger.info(kwargs)
+        self.wesar_weights = getattr(kwargs, "wesar_weights", False)
+        logger.info(f'initial wesar reparameterization : {self.wesar_weights}')
+
+        # alpha (scale factor)
+        self.embed_tokens_alpha = getattr(kwargs, "embed_tokens_alpha", None)
+        self.q_proj_alpha = getattr(kwargs, "q_proj_alpha", None)
+        self.k_proj_alpha = getattr(kwargs, "k_proj_alpha", None)
+        self.v_proj_alpha = getattr(kwargs, "v_proj_alpha", None)
+        self.o_proj_alpha = getattr(kwargs, "o_proj_alpha", None)
+        self.down_proj_alpha =  getattr(kwargs, "down_proj_alpha", None)
+        self.gate_up_proj_alpha =  getattr(kwargs, "gate_up_proj_alpha", None)
+        self.input_layernorm_alpha = getattr(kwargs, "input_layernorm_alpha", None)
+        self.post_attention_layernorm_alpha =  getattr(kwargs, "post_attention_layernorm_alpha", None)
+        self.norm_alpha = getattr(kwargs, "norm_alpha", None)
+        self.lm_head_alpha =  getattr(kwargs, "lm_head_alpha", None)
+        self.use_norm_alpha =  getattr(kwargs, "use_norm_alpha", False)
+        self.use_emb_alpha =  getattr(kwargs, "use_emb_alpha", False)
+
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, move it to 'rope_type'.
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        rope_config_validation(self)
+
+        self.multi_token_heads = multi_token_heads
+        self.multi_token_config_validation()
+
+
+
+        # moe
+        self.topk_method = getattr(kwargs, "topk_method", None)
+        self.scoring_func = getattr(kwargs, "scoring_func", None)
+        self.routed_scaling_factor = getattr(kwargs, "routed_scaling_factor", None)
+        self.norm_topk_prob = getattr(kwargs, "norm_topk_prob", None)
+        self.seq_aux = getattr(kwargs, "seq_aux", None)
+        self.hidden_act_moe =  getattr(kwargs, "hidden_act_moe", None)
+
+
+        self.n_group =  getattr(kwargs, "n_group", None)
+        self.n_routed_experts = getattr(kwargs, "n_routed_experts", None)
+        self.moe_intermediate_size =  getattr(kwargs, "moe_intermediate_size", None)
+        self.topk_group = getattr(kwargs, "topk_group", None)
+
+
+        self.use_fused_mlp =  getattr(kwargs, "use_fused_mlp", None)
+        self.use_moreh_moe =  getattr(kwargs, "use_moreh_moe", False)
+        self.continual_training =  getattr(kwargs, "continual_training", False)
+
+        # external
+        self.first_expansion =  getattr(kwargs, "first_expansion", False)
+        self.moe_layer =  getattr(kwargs, "moe_layer", False)
+
+
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+        logger.info(f' kwargs : {kwargs}')
+        logger.info(f'after wesar reparameterization : {self.wesar_weights}')
+
+    def multi_token_config_validation(self):
+        if self.multi_token_heads is not None:
+            assert isinstance(self.multi_token_heads, int) and self.multi_token_heads >= 1

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 219396,
+  "eos_token_id": [
+    219395,
+    219405
+  ],
+  "transformers_version": "4.51.3",
+  "use_cache": false
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3585a3263814f762598b6fc4464430d61b069742fa543e118d78bbefe01da08
+size 4952662512

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9380f28b7892e62f48fbd07e0d533ddc0fee44a7ba0b6111408a8a49e577996
+size 4966459400

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db220fa89bb483e4f8c029335034beb866b1f323adcac350f3d77fe546cad46c
+size 469808712

model.safetensors.index.json

@@ -0,0 +1,521 @@
+{
+  "metadata": {
+    "total_size": 10388873728
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.act_fn.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.act_fn.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.subln.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.act_fn.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.act_fn.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.lambda_k1": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.lambda_k2": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.lambda_q1": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.lambda_q2": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.subln.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.subln.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|beginoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275139d476909028da05d4ee035aba88f0ca0dbfd0d395f72b7fc80fd7782e19
+size 17264873

tokenizer_config.json

@@ -0,0 +1,1013 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "219395": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219396": {
+      "content": "<|beginoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219397": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219398": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219399": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219400": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219401": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219402": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219403": {
+      "content": "<|startofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219404": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219405": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219406": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219407": {
+      "content": "<|dummy_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219408": {
+      "content": "<|dummy_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219409": {
+      "content": "<|dummy_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219410": {
+      "content": "<|dummy_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219411": {
+      "content": "<|dummy_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219412": {
+      "content": "<|dummy_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219413": {
+      "content": "<|dummy_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219414": {
+      "content": "<|dummy_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219415": {
+      "content": "<|dummy_id_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219416": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219417": {
+      "content": "<|dummy_id_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219418": {
+      "content": "<|dummy_id_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219419": {
+      "content": "<|dummy_id_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219420": {
+      "content": "<|dummy_id_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219421": {
+      "content": "<|dummy_id_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219422": {
+      "content": "<|dummy_id_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219423": {
+      "content": "<|dummy_id_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219424": {
+      "content": "<|dummy_id_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219425": {
+      "content": "<|dummy_id_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219426": {
+      "content": "<|dummy_id_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219427": {
+      "content": "<|dummy_id_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219428": {
+      "content": "<|dummy_id_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219429": {
+      "content": "<|dummy_id_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219430": {
+      "content": "<|dummy_id_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219431": {
+      "content": "<|dummy_id_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219432": {
+      "content": "<|dummy_id_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219433": {
+      "content": "<|dummy_id_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219434": {
+      "content": "<|dummy_id_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219435": {
+      "content": "<|dummy_id_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219436": {
+      "content": "<|dummy_id_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219437": {
+      "content": "<|dummy_id_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219438": {
+      "content": "<|dummy_id_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219439": {
+      "content": "<|dummy_id_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219440": {
+      "content": "<|dummy_id_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219441": {
+      "content": "<|dummy_id_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219442": {
+      "content": "<|dummy_id_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219443": {
+      "content": "<|dummy_id_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219444": {
+      "content": "<|dummy_id_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219445": {
+      "content": "<|dummy_id_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219446": {
+      "content": "<|dummy_id_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219447": {
+      "content": "<|dummy_id_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219448": {
+      "content": "<|dummy_id_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219449": {
+      "content": "<|dummy_id_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219450": {
+      "content": "<|dummy_id_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219451": {
+      "content": "<|dummy_id_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219452": {
+      "content": "<|dummy_id_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219453": {
+      "content": "<|dummy_id_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219454": {
+      "content": "<|dummy_id_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219455": {
+      "content": "<|dummy_id_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219456": {
+      "content": "<|dummy_id_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219457": {
+      "content": "<|dummy_id_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219458": {
+      "content": "<|dummy_id_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219459": {
+      "content": "<|dummy_id_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219460": {
+      "content": "<|dummy_id_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219461": {
+      "content": "<|dummy_id_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219462": {
+      "content": "<|dummy_id_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219463": {
+      "content": "<|dummy_id_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219464": {
+      "content": "<|dummy_id_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219465": {
+      "content": "<|dummy_id_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219466": {
+      "content": "<|dummy_id_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219467": {
+      "content": "<|dummy_id_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219468": {
+      "content": "<|dummy_id_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219469": {
+      "content": "<|dummy_id_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219470": {
+      "content": "<|dummy_id_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219471": {
+      "content": "<|dummy_id_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219472": {
+      "content": "<|dummy_id_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219473": {
+      "content": "<|dummy_id_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219474": {
+      "content": "<|dummy_id_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219475": {
+      "content": "<|dummy_id_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219476": {
+      "content": "<|dummy_id_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219477": {
+      "content": "<|dummy_id_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219478": {
+      "content": "<|dummy_id_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219479": {
+      "content": "<|dummy_id_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219480": {
+      "content": "<|dummy_id_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219481": {
+      "content": "<|dummy_id_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219482": {
+      "content": "<|dummy_id_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219483": {
+      "content": "<|dummy_id_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219484": {
+      "content": "<|dummy_id_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219485": {
+      "content": "<|dummy_id_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219486": {
+      "content": "<|dummy_id_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219487": {
+      "content": "<|dummy_id_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219488": {
+      "content": "<|dummy_id_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219489": {
+      "content": "<|dummy_id_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219490": {
+      "content": "<|dummy_id_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219491": {
+      "content": "<|dummy_id_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219492": {
+      "content": "<|dummy_id_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219493": {
+      "content": "<|dummy_id_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219494": {
+      "content": "<|dummy_id_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219495": {
+      "content": "<|dummy_id_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219496": {
+      "content": "<|dummy_id_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219497": {
+      "content": "<|dummy_id_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219498": {
+      "content": "<|dummy_id_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219499": {
+      "content": "<|dummy_id_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219500": {
+      "content": "<|dummy_id_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219501": {
+      "content": "<|dummy_id_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219502": {
+      "content": "<|dummy_id_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219503": {
+      "content": "<|dummy_id_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219504": {
+      "content": "<|dummy_id_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219505": {
+      "content": "<|dummy_id_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219506": {
+      "content": "<|dummy_id_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219507": {
+      "content": "<|dummy_id_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219508": {
+      "content": "<|dummy_id_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219509": {
+      "content": "<|dummy_id_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219510": {
+      "content": "<|dummy_id_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219511": {
+      "content": "<|dummy_id_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219512": {
+      "content": "<|dummy_id_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219513": {
+      "content": "<|dummy_id_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219514": {
+      "content": "<|dummy_id_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219515": {
+      "content": "<|dummy_id_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219516": {
+      "content": "<|dummy_id_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219517": {
+      "content": "<|dummy_id_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219518": {
+      "content": "<|dummy_id_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219519": {
+      "content": "<|dummy_id_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|beginoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'assistant' and '</think>' in content %}{% set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}{% set content = content.split('</think>')[-1].lstrip('\n') %}{{ '<|startofturn|><|assistant|>\n\n<think>\n' + reasoning_content + '\n</think>\n\n' + content + '<|endofturn|>' }}{% else %}{{ '<|startofturn|><|' + message['role'] + '|>\n\n' + content + '<|endofturn|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|startofturn|><|assistant|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+}