Add files using upload-large-folder tool

config.json

@@ -0,0 +1,85 @@
+{
+  "activation_type": "silu",
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "architectures": [
+    "LlavaLladaForMaskedDiffusion"
+  ],
+  "attention_dropout": 0.0,
+  "attention_layer_norm": false,
+  "attention_layer_norm_with_affine": true,
+  "auto_map": {
+    "AutoConfig": "configuration_llada.LLaDAConfig",
+    "AutoModel": "modeling_llada.LLaDAModelLM",
+    "AutoModelForCausalLM": "modeling_llada.LLaDAModelLM"
+  },
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "llama",
+  "d_model": 4096,
+  "embedding_dropout": 0.0,
+  "embedding_size": 126464,
+  "eos_token_id": 126081,
+  "faster_token_stride": 10,
+  "flash_attention": false,
+  "force_sample": false,
+  "image_aspect_ratio": "square",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": null,
+  "image_split_resolution": null,
+  "include_bias": false,
+  "include_qkv_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "meta",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "input_emb_norm": false,
+  "layer_norm_type": "rms",
+  "layer_norm_with_affine": true,
+  "mask_token_id": 126336,
+  "max_sequence_length": 4096,
+  "mlp_hidden_size": 12288,
+  "mlp_ratio": 4,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_pooler_ratio": 2,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": null,
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "/data/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llada",
+  "multi_query_attention": null,
+  "n_heads": 32,
+  "n_kv_heads": 32,
+  "n_layers": 32,
+  "pad_token_id": 126081,
+  "pos_skipping_range": 4096,
+  "precision": "amp_bf16",
+  "resampler_type": null,
+  "residual_dropout": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope": true,
+  "rope_full_precision": true,
+  "rope_theta": 500000.0,
+  "scale_logits": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 126464,
+  "weight_tying": false
+}

configuration_llada.py

@@ -0,0 +1,463 @@
+"""
+LLaDA configuration
+"""
+from transformers import AutoConfig, PretrainedConfig
+
+from enum import Enum
+from os import PathLike
+from typing import Union
+from dataclasses import asdict, dataclass, field
+from glob import glob
+from pathlib import Path
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Optional,
+    Tuple,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
+
+
+__all__ = [
+    "ActivationType",
+    "ActivationCheckpointingStrategy",
+    "BlockType",
+    "LayerNormType",
+    "InitFnType",
+    "ModelConfig",
+]
+
+PathOrStr = Union[str, PathLike]
+
+
+class StrEnum(str, Enum):
+    """
+    This is equivalent to Python's :class:`enum.StrEnum` since version 3.11.
+    We include this here for compatibility with older version of Python.
+    """
+
+    def __str__(self) -> str:
+        return self.value
+
+    def __repr__(self) -> str:
+        return f"'{str(self)}'"
+
+
+class LayerNormType(StrEnum):
+    default = "default"
+    """
+    The default LayerNorm implementation, equivalent to PyTorch's built-in version.
+    """
+
+    low_precision = "low_precision"
+    """
+    A low-precision version of the default LayerNorm.
+    """
+
+    rms = "rms"
+    """
+    An RMSNorm implementation. When using ``torch.compile`` this is
+    probably the fastest implementation.
+    """
+
+    gemma_rms = "gemma_rms"
+    """
+    An RMSNorm implementation by gemmma. When using ``torch.compile`` this is
+    probably the fastest implementation.
+    """
+
+    amd_compatible = "amd_compatible"
+    """
+    LayerNorm implemented manually to work around an issue with ROCm.
+    """
+
+
+class ActivationType(StrEnum):
+    gelu = "gelu"
+    relu = "relu"
+    silu = "silu"
+    swiglu = "swiglu"
+
+
+class BlockType(StrEnum):
+    sequential = "sequential"
+    parallel = "parallel"
+
+    llama = "llama"
+    """
+    A block similar to the sequential block with slightly different
+    implementations of operations like attention to imitate the behavior of Llama.
+    """
+
+
+class InitFnType(StrEnum):
+    mitchell = "mitchell"
+    """
+    The strategy suggested to us by Mitchell Wortsman from UW.
+    This uses a truncated normal distribution with an adaptive standard deviation that depends
+    on the size of the weights as well as the depth of the layer.
+    """
+
+    normal = "normal"
+    """
+    All weights are initialized from the same normal distribution.
+    """
+
+    kaiming_normal = "kaiming_normal"
+    """
+    All weights are initialized with the Kaiming method from a normal distribution.
+    Note this currently won't work with FSDP.
+    """
+
+    fan_in = "fan_in"
+    """
+    "Fan-in variance scaling", i.e. normal with a standard deviation of ``1/sqrt(d_in)`` where ``d_in``
+    is the input dimensionality of the kernel.
+    """
+
+    full_megatron = "full_megatron"
+    """
+    This is what metaseq calls "full megatron init". It is the init used for Llama 2.
+    """
+
+
+@dataclass
+class ModelConfig():
+    """
+    LLaDA (model) configuration.
+    """
+
+    # Note that the defaults for these attributes are equivalent to the base GPT2 model.
+
+    d_model: int = 768
+    """
+    The hidden size of the model.
+    """
+
+    n_heads: int = 12
+    """
+    The number of self-attention heads.
+    """
+
+    n_kv_heads: Optional[int] = None
+    """
+    The number of heads to use for keys and values. Defaults to `n_heads`.
+    Set this to ``None`` or ``n_heads`` for normal multi-head attention.
+    Set this to 1 for multi-query attention.
+    Set it to some in-between value for Llama2-style grouped query attention.
+    """
+
+    n_layers: int = 12
+    """
+    The number of layers/blocks.
+    """
+
+    mlp_ratio: int = 4
+    """
+    The ratio of the inner MLP dimensionality to ``d_model``.
+    This is only used when ``mlp_hidden_size`` is not set.
+    """
+
+    mlp_hidden_size: Optional[int] = None
+    """
+    Set the exact hidden size for the MLP. Otherwise the inner MLP hidden size will be set to `mlp_ratio * d_model`.
+    """
+
+    activation_type: ActivationType = ActivationType.swiglu
+    """
+    The activation function to use within the MLP layers.
+    """
+
+    block_type: BlockType = BlockType.sequential
+    """
+    The transformer block implementation.
+    """
+
+    block_group_size: int = 1
+    """
+    The number of blocks to group together into a single parent block.
+    This has no affect on the number of parameters in the model and is only used to wrap groups
+    of blocks together with a single FSDP wrapper during training.
+    """
+
+    alibi: bool = False
+    """
+    If ``True``, use ALiBi embeddings. Mutually exclusive with ``rope``.
+    """
+
+    alibi_bias_max: float = 8.0
+    """
+    Maximum absolute value of ALiBi bias.
+    """
+
+    rope: bool = False
+    """
+    Use rotary positional embeddings (RoPE). Mutually exclusive with ``alibi``.
+    """
+
+    rope_full_precision: bool = True
+    """
+    If ``True``, apply RoPE embeddings at full precision regardless of the input type. Otherwise,
+    apply RoPE at the precision of the input.
+    """
+
+    flash_attention: bool = False
+    """
+    If ``True``, use ``FlashAttention``.
+    """
+
+    attention_dropout: float = 0.1
+    """
+    The dropout probability within the attention modules.
+    """
+
+    multi_query_attention: Optional[bool] = None
+    """
+    Use the Multi-Query formulation of attention used in PaLM. This reduces the number of parameters
+    and is more efficient during inference.
+    """
+
+    attention_layer_norm: bool = False
+    """
+    Apply layer norm to the keys and queries within the attention mechanism.
+    This can help stabilize training.
+    """
+
+    residual_dropout: float = 0.1
+    """
+    The dropout probability for the MLP and attention output within each block.
+    """
+
+    embedding_dropout: float = 0.1
+    """
+    The dropout probability for embeddings.
+    """
+
+    input_emb_norm: bool = False
+    """
+    An input hidden_states norm implementation by gemmma.
+    """
+
+    layer_norm_type: LayerNormType = LayerNormType.default
+    """
+    The layernorm implementation to use.
+    """
+
+    layer_norm_with_affine: bool = True
+    """
+    Whether to include bias and weight parameters for the layer norms.
+    This only affects layer norms that are immediately followed by a linear layer in the forward pass,
+    so everything except QK-norms. To turn off affines for QK norms as well, set :attr:`attention_layer_norm_with_affine`
+    to ``False``.
+    """
+
+    rms_norm_eps: float = 1e-05
+    """
+    The rms layernorm eps param.
+    """
+
+    attention_layer_norm_with_affine: bool = True
+    """
+    Toggle affine transform for the QK norms.
+    """
+
+    max_sequence_length: int = 1024
+    """
+    The maximum input sequence length supported by the model.
+    """
+
+    rope_theta: float = 10000.0
+    """
+    The rope base param.
+    """
+
+    include_qkv_bias: Optional[bool] = False
+    """
+    Whether or not to include bias parameters in qkv linear layers.
+    """
+
+    include_bias: bool = False
+    """
+    Whether or not to include bias parameters in linear layers.
+    In PaLM, they got rid of all bias terms because they found that large
+    models tend to have near 0 bias terms anyway.
+    """
+
+    bias_for_layer_norm: Optional[bool] = None
+    """
+    Whether or not to include bias parameters in layer norm.
+    This is separate from the include_bias parameter, because of a ROCm crash when biases are disabled in
+    layer norm.
+    When this is None (the default), it inherits the setting from include_bias.
+    """
+
+    scale_logits: bool = False
+    """
+    If ``True``, scale the output logits by ``1 / sqrt(d_model)``.
+    """
+
+    vocab_size: int = 50257
+    """
+    Vocabulary size of the model.
+    """
+
+    embedding_size: Optional[int] = 50304
+    """
+    The number of embeddings, i.e. the number of tokens. If set to ``None`` it will default
+    to ``vocab_size``. If ``vocab_size`` is not a multiple of 128, setting this to the
+    next multiple of 128 that's greater than ``vocab_size`` can improve throughput
+    substantially.
+    """
+
+    weight_tying: bool = True
+    """
+    Whether to tie output linear weights to the input embedding.
+    """
+
+    eos_token_id: int = 50256
+    """
+    The ID of the end-of-sentence special token.
+    """
+
+    pad_token_id: int = 50256
+    """
+    The ID of the token to use for padding. Defaults to the ID of the EOS token.
+    """
+
+    mask_token_id: Optional[int] = 50256
+    """
+    The ID of the token to use for mask token. Defaults to the ID of the EOS token.
+    """
+
+    init_device: Optional[str] = None
+    """
+    The torch device to use when initializing the model parameters, e.g. "cpu", "cuda:0", "meta".
+    """
+
+    init_fn: InitFnType = InitFnType.normal
+    """
+    The weight initialization strategy.
+    """
+
+    init_std: float = 0.02
+    """
+    The standard deviation to use when initializing weights with a "fixed distribution" ``init_fn``, such
+    as "normal".
+    """
+
+    init_cutoff_factor: Optional[float] = None
+    """
+    A positive factor used to scale the cutoff values when initializing weights with a "fixed distribution" ``init_fn``, such
+    as "normal". Setting this to None means values are not cutoff.
+    """
+
+    precision: Optional[str] = None
+    """
+    Precision used to train/evaluate with. You shouldn't set this directly.
+    See :data:`TrainConfig.precision` instead.
+    """
+
+    @property
+    def effective_n_kv_heads(self) -> int:
+        if self.n_kv_heads is None:
+            if self.multi_query_attention is True:
+                return 1
+            else:
+                return self.n_heads
+        else:
+            if self.multi_query_attention is None:
+                return self.n_kv_heads
+            if self.multi_query_attention:
+                n_kv_heads_should_be = 1
+            else:
+                n_kv_heads_should_be = self.n_heads
+            if self.n_kv_heads == n_kv_heads_should_be:
+                return n_kv_heads_should_be
+            else:
+                raise Exception(
+                    "You can't set `multi_query_attention` and `n_kv_heads` at the same time."
+                )
+
+class ActivationCheckpointingStrategy(StrEnum):
+    whole_layer = "whole_layer"
+    """
+    Checkpoint every transformer layer.
+    """
+
+    one_in_two = "one_in_two"
+    """
+    Checkpoint one in two transformer layers.
+    """
+
+    one_in_three = "one_in_three"
+    """
+    Checkpoint one in three transformer layers.
+    """
+
+    one_in_four = "one_in_four"
+    """
+    Checkpoint one in four transformer layers.
+    """
+    
+    two_in_three = "two_in_three"
+    """
+    Checkpoint two out of every three transformer layers.
+    """
+
+    three_in_four = "three_in_four"
+    """
+    Checkpoint three out of four of every transformer layers.
+    """
+
+    four_in_five = "four_in_five"
+    """
+    Checkpoint four out of five of every transformer layers.
+    """
+
+    nine_in_ten = "nine_in_ten"
+    """
+    Checkpoint nine out of ten of every transformer layers.
+    """
+
+    fine_grained = "fine_grained"
+    """
+    Focus checkpointing on where it is cheap to recompute and saves most memory.
+    """
+
+
+class LLaDAConfig(PretrainedConfig):
+    model_type = "llada"
+    keys_to_ignore_at_inference = ["past_key_values"]  # TODO: confirm
+
+    def __init__(self, use_cache: bool = False, **kwargs):
+        model_config = ModelConfig()
+        all_kwargs = model_config.__dict__
+        all_kwargs.update(kwargs)
+        all_kwargs.update({"use_cache": use_cache})
+        all_kwargs.update(
+            {
+                "architectures": all_kwargs.get("architectures", ["LLaDAModelLM"])
+            }
+        )
+        super().__init__(**all_kwargs)
+
+    @property
+    def num_attention_heads(self):
+        return self.n_heads
+
+    @property
+    def num_hidden_layers(self):
+        return self.n_layers
+
+    @property
+    def hidden_size(self):
+        return self.d_model
+
+
+# Register the config class so that it is available for transformer pipelines, auto-loading etc.
+AutoConfig.register("llada", LLaDAConfig)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 126080,
+  "eos_token_id": 126081,
+  "transformers_version": "4.50.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b2eed8d65170ede70c585376a1d20116e4c69f1bb78f5b929b1344aa91e641
+size 4995589944

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f07d9a62b3a8bea7553847447f66e30e026a4e7319fdccbb501056e033c6a04
+size 4999819552

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0336df823301742d2bc44a0130a9bde6a1e489018508ae984fda51c0ba7c0d27
+size 4999802728

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4c583e6c5c9cf5a04c63b0c9c60479c3df6486a83850eb061659a87cd57a22
+size 1874563264

model.safetensors.index.json

@@ -0,0 +1,724 @@
+{
+  "metadata": {
+    "total_size": 16869674048
+  },
+  "weight_map": {
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.blocks.0.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.0.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.1.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.10.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.10.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.11.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.12.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.13.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.14.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.15.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.16.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.17.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.18.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.19.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.2.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.2.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.20.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.attn_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.20.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.20.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.21.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.21.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.22.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.23.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.24.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.25.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.26.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.27.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.28.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.29.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.3.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.3.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.30.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.30.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.attn_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.attn_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_norm.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_out.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.ff_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.31.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.transformer.blocks.4.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.4.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.5.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.6.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.7.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.attn_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_norm.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.ff_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.8.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.9.attn_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.attn_out.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_norm.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_out.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.ff_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.blocks.9.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.transformer.ff_out.weight": "model-00004-of-00004.safetensors",
+    "model.transformer.ln_f.weight": "model-00001-of-00004.safetensors",
+    "model.transformer.wte.weight": "model-00001-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<role>",
+    "</role>",
+    "<|arithmetic_start|>",
+    "<|arithmetic_end|>",
+    "<|number_start|>",
+    "<|number_end|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2184 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "126080": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126081": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126082": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126083": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126084": {
+      "content": "<|reserved_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126085": {
+      "content": "<|reserved_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126086": {
+      "content": "<|reserved_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126087": {
+      "content": "<|reserved_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126088": {
+      "content": "<|reserved_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126089": {
+      "content": "<|reserved_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126090": {
+      "content": "<|reserved_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126091": {
+      "content": "<|reserved_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126092": {
+      "content": "<|reserved_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126093": {
+      "content": "<|reserved_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126094": {
+      "content": "<|reserved_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126095": {
+      "content": "<|reserved_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126096": {
+      "content": "<|reserved_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126097": {
+      "content": "<|reserved_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126098": {
+      "content": "<|reserved_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126099": {
+      "content": "<|reserved_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126100": {
+      "content": "<|reserved_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126101": {
+      "content": "<|reserved_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126102": {
+      "content": "<|reserved_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126103": {
+      "content": "<|reserved_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126104": {
+      "content": "<|reserved_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126105": {
+      "content": "<|reserved_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126106": {
+      "content": "<|reserved_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126107": {
+      "content": "<|reserved_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126108": {
+      "content": "<|reserved_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126109": {
+      "content": "<|reserved_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126110": {
+      "content": "<|reserved_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126111": {
+      "content": "<|reserved_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126112": {
+      "content": "<|reserved_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126113": {
+      "content": "<|reserved_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126114": {
+      "content": "<|reserved_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126115": {
+      "content": "<|reserved_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126116": {
+      "content": "<|reserved_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126117": {
+      "content": "<|reserved_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126118": {
+      "content": "<|reserved_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126119": {
+      "content": "<|reserved_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126120": {
+      "content": "<|reserved_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126121": {
+      "content": "<|reserved_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126122": {
+      "content": "<|reserved_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126123": {
+      "content": "<|reserved_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126124": {
+      "content": "<|reserved_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126125": {
+      "content": "<|reserved_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126126": {
+      "content": "<|reserved_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126127": {
+      "content": "<|reserved_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126128": {
+      "content": "<|reserved_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126129": {
+      "content": "<|reserved_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126130": {
+      "content": "<|reserved_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126131": {
+      "content": "<|reserved_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126132": {
+      "content": "<|reserved_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126133": {
+      "content": "<|reserved_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126134": {
+      "content": "<|reserved_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126135": {
+      "content": "<|reserved_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126136": {
+      "content": "<|reserved_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126137": {
+      "content": "<|reserved_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126138": {
+      "content": "<|reserved_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126139": {
+      "content": "<|reserved_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126140": {
+      "content": "<|reserved_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126141": {
+      "content": "<|reserved_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126142": {
+      "content": "<|reserved_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126143": {
+      "content": "<|reserved_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126144": {
+      "content": "<|reserved_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126145": {
+      "content": "<|reserved_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126146": {
+      "content": "<|reserved_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126147": {
+      "content": "<|reserved_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126148": {
+      "content": "<|reserved_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126149": {
+      "content": "<|reserved_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126150": {
+      "content": "<|reserved_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126151": {
+      "content": "<|reserved_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126152": {
+      "content": "<|reserved_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126153": {
+      "content": "<|reserved_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126154": {
+      "content": "<|reserved_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126155": {
+      "content": "<|reserved_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126156": {
+      "content": "<|reserved_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126157": {
+      "content": "<|reserved_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126158": {
+      "content": "<|reserved_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126159": {
+      "content": "<|reserved_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126160": {
+      "content": "<|reserved_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126161": {
+      "content": "<|reserved_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126162": {
+      "content": "<|reserved_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126163": {
+      "content": "<|reserved_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126164": {
+      "content": "<|reserved_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126165": {
+      "content": "<|reserved_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126166": {
+      "content": "<|reserved_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126167": {
+      "content": "<|reserved_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126168": {
+      "content": "<|reserved_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126169": {
+      "content": "<|reserved_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126170": {
+      "content": "<|reserved_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126171": {
+      "content": "<|reserved_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126172": {
+      "content": "<|reserved_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126173": {
+      "content": "<|reserved_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126174": {
+      "content": "<|reserved_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126175": {
+      "content": "<|reserved_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126176": {
+      "content": "<|reserved_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126177": {
+      "content": "<|reserved_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126178": {
+      "content": "<|reserved_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126179": {
+      "content": "<|reserved_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126180": {
+      "content": "<|reserved_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126181": {
+      "content": "<|reserved_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126182": {
+      "content": "<|reserved_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126183": {
+      "content": "<|reserved_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126184": {
+      "content": "<|reserved_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126185": {
+      "content": "<|reserved_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126186": {
+      "content": "<|reserved_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126187": {
+      "content": "<|reserved_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126188": {
+      "content": "<|reserved_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126189": {
+      "content": "<|reserved_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126190": {
+      "content": "<|reserved_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126191": {
+      "content": "<|reserved_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126192": {
+      "content": "<|reserved_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126193": {
+      "content": "<|reserved_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126194": {
+      "content": "<|reserved_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126195": {
+      "content": "<|reserved_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126196": {
+      "content": "<|reserved_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126197": {
+      "content": "<|reserved_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126198": {
+      "content": "<|reserved_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126199": {
+      "content": "<|reserved_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126200": {
+      "content": "<|reserved_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126201": {
+      "content": "<|reserved_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126202": {
+      "content": "<|reserved_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126203": {
+      "content": "<|reserved_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126204": {
+      "content": "<|reserved_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126205": {
+      "content": "<|reserved_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126206": {
+      "content": "<|reserved_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126207": {
+      "content": "<|reserved_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126208": {
+      "content": "<|reserved_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126209": {
+      "content": "<|reserved_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126210": {
+      "content": "<|reserved_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126211": {
+      "content": "<|reserved_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126212": {
+      "content": "<|reserved_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126213": {
+      "content": "<|reserved_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126214": {
+      "content": "<|reserved_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126215": {
+      "content": "<|reserved_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126216": {
+      "content": "<|reserved_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126217": {
+      "content": "<|reserved_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126218": {
+      "content": "<|reserved_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126219": {
+      "content": "<|reserved_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126220": {
+      "content": "<|reserved_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126221": {
+      "content": "<|reserved_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126222": {
+      "content": "<|reserved_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126223": {
+      "content": "<|reserved_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126224": {
+      "content": "<|reserved_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126225": {
+      "content": "<|reserved_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126226": {
+      "content": "<|reserved_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126227": {
+      "content": "<|reserved_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126228": {
+      "content": "<|reserved_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126229": {
+      "content": "<|reserved_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126230": {
+      "content": "<|reserved_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126231": {
+      "content": "<|reserved_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126232": {
+      "content": "<|reserved_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126233": {
+      "content": "<|reserved_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126234": {
+      "content": "<|reserved_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126235": {
+      "content": "<|reserved_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126236": {
+      "content": "<|reserved_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126237": {
+      "content": "<|reserved_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126238": {
+      "content": "<|reserved_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126239": {
+      "content": "<|reserved_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126240": {
+      "content": "<|reserved_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126241": {
+      "content": "<|reserved_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126242": {
+      "content": "<|reserved_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126243": {
+      "content": "<|reserved_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126244": {
+      "content": "<|reserved_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126245": {
+      "content": "<|reserved_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126246": {
+      "content": "<|reserved_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126247": {
+      "content": "<|reserved_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126248": {
+      "content": "<|reserved_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126249": {
+      "content": "<|reserved_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126250": {
+      "content": "<|reserved_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126251": {
+      "content": "<|reserved_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126252": {
+      "content": "<|reserved_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126253": {
+      "content": "<|reserved_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126254": {
+      "content": "<|reserved_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126255": {
+      "content": "<|reserved_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126256": {
+      "content": "<|reserved_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126257": {
+      "content": "<|reserved_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126258": {
+      "content": "<|reserved_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126259": {
+      "content": "<|reserved_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126260": {
+      "content": "<|reserved_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126261": {
+      "content": "<|reserved_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126262": {
+      "content": "<|reserved_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126263": {
+      "content": "<|reserved_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126264": {
+      "content": "<|reserved_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126265": {
+      "content": "<|reserved_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126266": {
+      "content": "<|reserved_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126267": {
+      "content": "<|reserved_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126268": {
+      "content": "<|reserved_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126269": {
+      "content": "<|reserved_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126270": {
+      "content": "<|reserved_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126271": {
+      "content": "<|reserved_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126272": {
+      "content": "<|reserved_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126273": {
+      "content": "<|reserved_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126274": {
+      "content": "<|reserved_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126275": {
+      "content": "<|reserved_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126276": {
+      "content": "<|reserved_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126277": {
+      "content": "<|reserved_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126278": {
+      "content": "<|reserved_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126279": {
+      "content": "<|reserved_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126280": {
+      "content": "<|reserved_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126281": {
+      "content": "<|reserved_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126282": {
+      "content": "<|reserved_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126283": {
+      "content": "<|reserved_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126284": {
+      "content": "<|reserved_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126285": {
+      "content": "<|reserved_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126286": {
+      "content": "<|reserved_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126287": {
+      "content": "<|reserved_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126288": {
+      "content": "<|reserved_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126289": {
+      "content": "<|reserved_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126290": {
+      "content": "<|reserved_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126291": {
+      "content": "<|reserved_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126292": {
+      "content": "<|reserved_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126293": {
+      "content": "<|reserved_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126294": {
+      "content": "<|reserved_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126295": {
+      "content": "<|reserved_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126296": {
+      "content": "<|reserved_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126297": {
+      "content": "<|reserved_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126298": {
+      "content": "<|reserved_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126299": {
+      "content": "<|reserved_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126300": {
+      "content": "<|reserved_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126301": {
+      "content": "<|reserved_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126302": {
+      "content": "<|reserved_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126303": {
+      "content": "<|reserved_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126304": {
+      "content": "<|reserved_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126305": {
+      "content": "<|reserved_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126306": {
+      "content": "<|reserved_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126307": {
+      "content": "<|reserved_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126308": {
+      "content": "<|reserved_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126309": {
+      "content": "<|reserved_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126310": {
+      "content": "<|reserved_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126311": {
+      "content": "<|reserved_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126312": {
+      "content": "<|reserved_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126313": {
+      "content": "<|reserved_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126314": {
+      "content": "<|reserved_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126315": {
+      "content": "<|reserved_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126316": {
+      "content": "<|reserved_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126317": {
+      "content": "<|reserved_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126318": {
+      "content": "<|reserved_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126319": {
+      "content": "<|reserved_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126320": {
+      "content": "<|reserved_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126321": {
+      "content": "<|reserved_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126322": {
+      "content": "<|reserved_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126323": {
+      "content": "<|reserved_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126324": {
+      "content": "<|reserved_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126325": {
+      "content": "<|reserved_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126326": {
+      "content": "<|reserved_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126327": {
+      "content": "<|reserved_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126328": {
+      "content": "<|reserved_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126329": {
+      "content": "<|reserved_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126330": {
+      "content": "<|reserved_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126331": {
+      "content": "<|reserved_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126332": {
+      "content": "<|reserved_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126333": {
+      "content": "<|reserved_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126334": {
+      "content": "<|reserved_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126335": {
+      "content": "<|reserved_token_251|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126336": {
+      "content": "<|mdm_mask|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126337": {
+      "content": "<|reserved_token_253|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126338": {
+      "content": "<|reserved_token_254|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126339": {
+      "content": "<|reserved_token_255|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126340": {
+      "content": "<role>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126341": {
+      "content": "</role>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126342": {
+      "content": "<|arithmetic_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126343": {
+      "content": "<|arithmetic_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126344": {
+      "content": "<|number_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126345": {
+      "content": "<|number_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126346": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126347": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126348": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<role>",
+    "</role>",
+    "<|arithmetic_start|>",
+    "<|arithmetic_end|>",
+    "<|number_start|>",
+    "<|number_end|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "gmask_token": "[gMASK]",
+  "merges_file": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "trust_remote_code": true
+}

trainer_state.json

@@ -0,0 +1,1387 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.964980544747082,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01556420233463035,
+      "grad_norm": 32.7662513325928,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.0427,
+      "step": 1
+    },
+    {
+      "epoch": 0.0311284046692607,
+      "grad_norm": 14.17953242397471,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.8704,
+      "step": 2
+    },
+    {
+      "epoch": 0.04669260700389105,
+      "grad_norm": 9.581323731857186,
+      "learning_rate": 1e-05,
+      "loss": 2.0032,
+      "step": 3
+    },
+    {
+      "epoch": 0.0622568093385214,
+      "grad_norm": 12.804841760907372,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.2126,
+      "step": 4
+    },
+    {
+      "epoch": 0.07782101167315175,
+      "grad_norm": 8.478925783183458,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.4769,
+      "step": 5
+    },
+    {
+      "epoch": 0.0933852140077821,
+      "grad_norm": 8.969266052384613,
+      "learning_rate": 2e-05,
+      "loss": 1.5752,
+      "step": 6
+    },
+    {
+      "epoch": 0.10894941634241245,
+      "grad_norm": 11.83099546071694,
+      "learning_rate": 1.999871626303739e-05,
+      "loss": 1.5588,
+      "step": 7
+    },
+    {
+      "epoch": 0.1245136186770428,
+      "grad_norm": 5.954526723326734,
+      "learning_rate": 1.999486541836746e-05,
+      "loss": 1.3619,
+      "step": 8
+    },
+    {
+      "epoch": 0.14007782101167315,
+      "grad_norm": 36.01845182362445,
+      "learning_rate": 1.9988448564539475e-05,
+      "loss": 1.3373,
+      "step": 9
+    },
+    {
+      "epoch": 0.1556420233463035,
+      "grad_norm": 9.862509446330417,
+      "learning_rate": 1.9979467532120636e-05,
+      "loss": 1.8391,
+      "step": 10
+    },
+    {
+      "epoch": 0.17120622568093385,
+      "grad_norm": 6.924375728787968,
+      "learning_rate": 1.99679248831739e-05,
+      "loss": 1.7063,
+      "step": 11
+    },
+    {
+      "epoch": 0.1867704280155642,
+      "grad_norm": 5.947859490849787,
+      "learning_rate": 1.9953823910527057e-05,
+      "loss": 1.3137,
+      "step": 12
+    },
+    {
+      "epoch": 0.20233463035019456,
+      "grad_norm": 9.376302417818316,
+      "learning_rate": 1.9937168636833405e-05,
+      "loss": 1.4841,
+      "step": 13
+    },
+    {
+      "epoch": 0.2178988326848249,
+      "grad_norm": 8.09315137157763,
+      "learning_rate": 1.9917963813424154e-05,
+      "loss": 1.6061,
+      "step": 14
+    },
+    {
+      "epoch": 0.23346303501945526,
+      "grad_norm": 12.912871635467674,
+      "learning_rate": 1.9896214918953003e-05,
+      "loss": 1.5974,
+      "step": 15
+    },
+    {
+      "epoch": 0.2490272373540856,
+      "grad_norm": 4.890429692775311,
+      "learning_rate": 1.9871928157833235e-05,
+      "loss": 1.3604,
+      "step": 16
+    },
+    {
+      "epoch": 0.26459143968871596,
+      "grad_norm": 5.96078805337046,
+      "learning_rate": 1.9845110458467724e-05,
+      "loss": 1.4205,
+      "step": 17
+    },
+    {
+      "epoch": 0.2801556420233463,
+      "grad_norm": 5.406312981626749,
+      "learning_rate": 1.981576947127245e-05,
+      "loss": 1.3691,
+      "step": 18
+    },
+    {
+      "epoch": 0.29571984435797666,
+      "grad_norm": 6.229338294974077,
+      "learning_rate": 1.978391356649404e-05,
+      "loss": 1.4662,
+      "step": 19
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 7.078018638767833,
+      "learning_rate": 1.9749551831821917e-05,
+      "loss": 1.4734,
+      "step": 20
+    },
+    {
+      "epoch": 0.32684824902723736,
+      "grad_norm": 11.02898750969552,
+      "learning_rate": 1.971269406979584e-05,
+      "loss": 1.3636,
+      "step": 21
+    },
+    {
+      "epoch": 0.3424124513618677,
+      "grad_norm": 6.82235626712361,
+      "learning_rate": 1.9673350795009468e-05,
+      "loss": 1.5607,
+      "step": 22
+    },
+    {
+      "epoch": 0.35797665369649806,
+      "grad_norm": 8.481695271045934,
+      "learning_rate": 1.963153323111082e-05,
+      "loss": 1.2882,
+      "step": 23
+    },
+    {
+      "epoch": 0.3735408560311284,
+      "grad_norm": 17.63369186879554,
+      "learning_rate": 1.958725330760044e-05,
+      "loss": 1.5022,
+      "step": 24
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 17.68569390194203,
+      "learning_rate": 1.9540523656428223e-05,
+      "loss": 1.2848,
+      "step": 25
+    },
+    {
+      "epoch": 0.4046692607003891,
+      "grad_norm": 6.641749083734281,
+      "learning_rate": 1.9491357608389824e-05,
+      "loss": 1.2358,
+      "step": 26
+    },
+    {
+      "epoch": 0.42023346303501946,
+      "grad_norm": 23.867198010532427,
+      "learning_rate": 1.9439769189323727e-05,
+      "loss": 1.2404,
+      "step": 27
+    },
+    {
+      "epoch": 0.4357976653696498,
+      "grad_norm": 6.690231465484989,
+      "learning_rate": 1.9385773116110015e-05,
+      "loss": 1.3622,
+      "step": 28
+    },
+    {
+      "epoch": 0.45136186770428016,
+      "grad_norm": 7.267926238407661,
+      "learning_rate": 1.9329384792472036e-05,
+      "loss": 1.3815,
+      "step": 29
+    },
+    {
+      "epoch": 0.4669260700389105,
+      "grad_norm": 7.371143249720988,
+      "learning_rate": 1.9270620304582077e-05,
+      "loss": 1.4497,
+      "step": 30
+    },
+    {
+      "epoch": 0.48249027237354086,
+      "grad_norm": 5.739368570493641,
+      "learning_rate": 1.92094964164724e-05,
+      "loss": 1.439,
+      "step": 31
+    },
+    {
+      "epoch": 0.4980544747081712,
+      "grad_norm": 10.712092924918982,
+      "learning_rate": 1.9146030565252894e-05,
+      "loss": 1.2185,
+      "step": 32
+    },
+    {
+      "epoch": 0.5136186770428015,
+      "grad_norm": 5.745736001033042,
+      "learning_rate": 1.9080240856136675e-05,
+      "loss": 1.4049,
+      "step": 33
+    },
+    {
+      "epoch": 0.5291828793774319,
+      "grad_norm": 7.632465200177505,
+      "learning_rate": 1.9012146057275168e-05,
+      "loss": 1.5059,
+      "step": 34
+    },
+    {
+      "epoch": 0.5447470817120622,
+      "grad_norm": 8.286309897189899,
+      "learning_rate": 1.8941765594403975e-05,
+      "loss": 1.4689,
+      "step": 35
+    },
+    {
+      "epoch": 0.5603112840466926,
+      "grad_norm": 8.480450264883203,
+      "learning_rate": 1.886911954530124e-05,
+      "loss": 1.5331,
+      "step": 36
+    },
+    {
+      "epoch": 0.5758754863813229,
+      "grad_norm": 9.499572491510447,
+      "learning_rate": 1.879422863405995e-05,
+      "loss": 1.635,
+      "step": 37
+    },
+    {
+      "epoch": 0.5914396887159533,
+      "grad_norm": 9.489789008744502,
+      "learning_rate": 1.8717114225175858e-05,
+      "loss": 1.4844,
+      "step": 38
+    },
+    {
+      "epoch": 0.6070038910505836,
+      "grad_norm": 7.2947137328088765,
+      "learning_rate": 1.863779831745276e-05,
+      "loss": 1.4507,
+      "step": 39
+    },
+    {
+      "epoch": 0.622568093385214,
+      "grad_norm": 5.913323265251484,
+      "learning_rate": 1.8556303537726753e-05,
+      "loss": 1.6038,
+      "step": 40
+    },
+    {
+      "epoch": 0.6381322957198443,
+      "grad_norm": 14.132278657345845,
+      "learning_rate": 1.8472653134411388e-05,
+      "loss": 1.3738,
+      "step": 41
+    },
+    {
+      "epoch": 0.6536964980544747,
+      "grad_norm": 7.698733116161007,
+      "learning_rate": 1.8386870970865488e-05,
+      "loss": 1.1948,
+      "step": 42
+    },
+    {
+      "epoch": 0.669260700389105,
+      "grad_norm": 6.593898707009616,
+      "learning_rate": 1.8298981518585514e-05,
+      "loss": 1.2161,
+      "step": 43
+    },
+    {
+      "epoch": 0.6848249027237354,
+      "grad_norm": 8.732218414278748,
+      "learning_rate": 1.8209009850224465e-05,
+      "loss": 1.3516,
+      "step": 44
+    },
+    {
+      "epoch": 0.7003891050583657,
+      "grad_norm": 10.91781491470466,
+      "learning_rate": 1.811698163243929e-05,
+      "loss": 1.3615,
+      "step": 45
+    },
+    {
+      "epoch": 0.7159533073929961,
+      "grad_norm": 10.205838168734168,
+      "learning_rate": 1.8022923118568827e-05,
+      "loss": 1.4948,
+      "step": 46
+    },
+    {
+      "epoch": 0.7315175097276264,
+      "grad_norm": 17.343787523950684,
+      "learning_rate": 1.7926861141144393e-05,
+      "loss": 1.4923,
+      "step": 47
+    },
+    {
+      "epoch": 0.7470817120622568,
+      "grad_norm": 6.218713745426841,
+      "learning_rate": 1.782882310423512e-05,
+      "loss": 1.3801,
+      "step": 48
+    },
+    {
+      "epoch": 0.7626459143968871,
+      "grad_norm": 9.930901357054527,
+      "learning_rate": 1.7728836975630283e-05,
+      "loss": 1.4591,
+      "step": 49
+    },
+    {
+      "epoch": 0.7782101167315175,
+      "grad_norm": 10.565666651397537,
+      "learning_rate": 1.7626931278860773e-05,
+      "loss": 1.2283,
+      "step": 50
+    },
+    {
+      "epoch": 0.7937743190661478,
+      "grad_norm": 7.173094908653802,
+      "learning_rate": 1.752313508506208e-05,
+      "loss": 1.1787,
+      "step": 51
+    },
+    {
+      "epoch": 0.8093385214007782,
+      "grad_norm": 7.454713889992053,
+      "learning_rate": 1.7417478004680982e-05,
+      "loss": 1.387,
+      "step": 52
+    },
+    {
+      "epoch": 0.8249027237354085,
+      "grad_norm": 8.888727310362047,
+      "learning_rate": 1.730999017902848e-05,
+      "loss": 1.363,
+      "step": 53
+    },
+    {
+      "epoch": 0.8404669260700389,
+      "grad_norm": 8.910897747960528,
+      "learning_rate": 1.720070227168118e-05,
+      "loss": 1.4924,
+      "step": 54
+    },
+    {
+      "epoch": 0.8560311284046692,
+      "grad_norm": 8.560591680367171,
+      "learning_rate": 1.708964545973382e-05,
+      "loss": 1.5208,
+      "step": 55
+    },
+    {
+      "epoch": 0.8715953307392996,
+      "grad_norm": 6.31006260674449,
+      "learning_rate": 1.6976851424905153e-05,
+      "loss": 1.1552,
+      "step": 56
+    },
+    {
+      "epoch": 0.8871595330739299,
+      "grad_norm": 15.810845104599778,
+      "learning_rate": 1.6862352344500004e-05,
+      "loss": 1.2454,
+      "step": 57
+    },
+    {
+      "epoch": 0.9027237354085603,
+      "grad_norm": 6.767459348182446,
+      "learning_rate": 1.674618088222985e-05,
+      "loss": 1.2886,
+      "step": 58
+    },
+    {
+      "epoch": 0.9182879377431906,
+      "grad_norm": 10.51614814940254,
+      "learning_rate": 1.6628370178894734e-05,
+      "loss": 1.2644,
+      "step": 59
+    },
+    {
+      "epoch": 0.933852140077821,
+      "grad_norm": 7.047043052174269,
+      "learning_rate": 1.6508953842928966e-05,
+      "loss": 1.443,
+      "step": 60
+    },
+    {
+      "epoch": 0.9494163424124513,
+      "grad_norm": 8.579327238483026,
+      "learning_rate": 1.638796594081354e-05,
+      "loss": 1.3322,
+      "step": 61
+    },
+    {
+      "epoch": 0.9649805447470817,
+      "grad_norm": 7.0287097887612235,
+      "learning_rate": 1.626544098735777e-05,
+      "loss": 1.4198,
+      "step": 62
+    },
+    {
+      "epoch": 0.980544747081712,
+      "grad_norm": 16.693418616763456,
+      "learning_rate": 1.614141393585313e-05,
+      "loss": 1.4243,
+      "step": 63
+    },
+    {
+      "epoch": 0.9961089494163424,
+      "grad_norm": 4.4493625007162185,
+      "learning_rate": 1.601592016810193e-05,
+      "loss": 1.0317,
+      "step": 64
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.4493625007162185,
+      "learning_rate": 1.588899548432377e-05,
+      "loss": 0.3818,
+      "step": 65
+    },
+    {
+      "epoch": 1.0155642023346303,
+      "grad_norm": 14.571145059681054,
+      "learning_rate": 1.5760676092942663e-05,
+      "loss": 1.3258,
+      "step": 66
+    },
+    {
+      "epoch": 1.0311284046692606,
+      "grad_norm": 7.149351806597666,
+      "learning_rate": 1.563099860025766e-05,
+      "loss": 1.2366,
+      "step": 67
+    },
+    {
+      "epoch": 1.046692607003891,
+      "grad_norm": 40.50757660945441,
+      "learning_rate": 1.55e-05,
+      "loss": 1.6179,
+      "step": 68
+    },
+    {
+      "epoch": 1.0622568093385214,
+      "grad_norm": 15.44110442369705,
+      "learning_rate": 1.5367717662779732e-05,
+      "loss": 1.3405,
+      "step": 69
+    },
+    {
+      "epoch": 1.0778210116731517,
+      "grad_norm": 6.675357357971338,
+      "learning_rate": 1.5234189325424802e-05,
+      "loss": 1.1276,
+      "step": 70
+    },
+    {
+      "epoch": 1.0933852140077822,
+      "grad_norm": 7.1518156856898605,
+      "learning_rate": 1.5099453080215705e-05,
+      "loss": 1.2737,
+      "step": 71
+    },
+    {
+      "epoch": 1.1089494163424125,
+      "grad_norm": 6.2755998715712815,
+      "learning_rate": 1.4963547364018711e-05,
+      "loss": 1.2964,
+      "step": 72
+    },
+    {
+      "epoch": 1.1245136186770428,
+      "grad_norm": 7.749171240376019,
+      "learning_rate": 1.4826510947320767e-05,
+      "loss": 1.2542,
+      "step": 73
+    },
+    {
+      "epoch": 1.140077821011673,
+      "grad_norm": 8.188433813273727,
+      "learning_rate": 1.4688382923169289e-05,
+      "loss": 1.2587,
+      "step": 74
+    },
+    {
+      "epoch": 1.1556420233463034,
+      "grad_norm": 7.386225279732122,
+      "learning_rate": 1.4549202696019868e-05,
+      "loss": 1.3309,
+      "step": 75
+    },
+    {
+      "epoch": 1.171206225680934,
+      "grad_norm": 6.253316144967461,
+      "learning_rate": 1.4409009970495184e-05,
+      "loss": 1.3574,
+      "step": 76
+    },
+    {
+      "epoch": 1.1867704280155642,
+      "grad_norm": 10.042142885418704,
+      "learning_rate": 1.4267844740058273e-05,
+      "loss": 1.1808,
+      "step": 77
+    },
+    {
+      "epoch": 1.2023346303501945,
+      "grad_norm": 8.752169534398908,
+      "learning_rate": 1.4125747275603384e-05,
+      "loss": 1.2535,
+      "step": 78
+    },
+    {
+      "epoch": 1.217898832684825,
+      "grad_norm": 5.922268212950014,
+      "learning_rate": 1.3982758113967723e-05,
+      "loss": 1.4928,
+      "step": 79
+    },
+    {
+      "epoch": 1.2334630350194553,
+      "grad_norm": 13.340943215095326,
+      "learning_rate": 1.3838918046367302e-05,
+      "loss": 1.5576,
+      "step": 80
+    },
+    {
+      "epoch": 1.2490272373540856,
+      "grad_norm": 11.447188182283101,
+      "learning_rate": 1.3694268106760225e-05,
+      "loss": 1.3702,
+      "step": 81
+    },
+    {
+      "epoch": 1.264591439688716,
+      "grad_norm": 8.785930153191286,
+      "learning_rate": 1.3548849560140735e-05,
+      "loss": 1.5769,
+      "step": 82
+    },
+    {
+      "epoch": 1.2801556420233462,
+      "grad_norm": 11.289308481687042,
+      "learning_rate": 1.3402703890767365e-05,
+      "loss": 1.4041,
+      "step": 83
+    },
+    {
+      "epoch": 1.2957198443579767,
+      "grad_norm": 6.0701513028110865,
+      "learning_rate": 1.3255872790328485e-05,
+      "loss": 1.2474,
+      "step": 84
+    },
+    {
+      "epoch": 1.311284046692607,
+      "grad_norm": 15.420406437695464,
+      "learning_rate": 1.310839814604874e-05,
+      "loss": 1.3971,
+      "step": 85
+    },
+    {
+      "epoch": 1.3268482490272373,
+      "grad_norm": 11.112901019437691,
+      "learning_rate": 1.2960322028739664e-05,
+      "loss": 1.292,
+      "step": 86
+    },
+    {
+      "epoch": 1.3424124513618678,
+      "grad_norm": 6.574313635072488,
+      "learning_rate": 1.2811686680797942e-05,
+      "loss": 1.5592,
+      "step": 87
+    },
+    {
+      "epoch": 1.3579766536964981,
+      "grad_norm": 19.9661703497788,
+      "learning_rate": 1.2662534504154707e-05,
+      "loss": 1.5115,
+      "step": 88
+    },
+    {
+      "epoch": 1.3735408560311284,
+      "grad_norm": 18.38165853721984,
+      "learning_rate": 1.2512908048179336e-05,
+      "loss": 1.5681,
+      "step": 89
+    },
+    {
+      "epoch": 1.3891050583657587,
+      "grad_norm": 7.567686089019195,
+      "learning_rate": 1.236284999754119e-05,
+      "loss": 1.2417,
+      "step": 90
+    },
+    {
+      "epoch": 1.404669260700389,
+      "grad_norm": 12.905705238689295,
+      "learning_rate": 1.221240316003275e-05,
+      "loss": 1.2854,
+      "step": 91
+    },
+    {
+      "epoch": 1.4202334630350195,
+      "grad_norm": 20.818267922715442,
+      "learning_rate": 1.2061610454357618e-05,
+      "loss": 1.5286,
+      "step": 92
+    },
+    {
+      "epoch": 1.4357976653696498,
+      "grad_norm": 6.109213052045277,
+      "learning_rate": 1.1910514897886892e-05,
+      "loss": 1.3168,
+      "step": 93
+    },
+    {
+      "epoch": 1.45136186770428,
+      "grad_norm": 15.101872320411488,
+      "learning_rate": 1.1759159594387404e-05,
+      "loss": 1.5504,
+      "step": 94
+    },
+    {
+      "epoch": 1.4669260700389106,
+      "grad_norm": 6.233434571455187,
+      "learning_rate": 1.1607587721725288e-05,
+      "loss": 1.5917,
+      "step": 95
+    },
+    {
+      "epoch": 1.482490272373541,
+      "grad_norm": 9.122907207075865,
+      "learning_rate": 1.1455842519548417e-05,
+      "loss": 1.53,
+      "step": 96
+    },
+    {
+      "epoch": 1.4980544747081712,
+      "grad_norm": 7.271922289011854,
+      "learning_rate": 1.1303967276951215e-05,
+      "loss": 1.3232,
+      "step": 97
+    },
+    {
+      "epoch": 1.5136186770428015,
+      "grad_norm": 7.525926983479133,
+      "learning_rate": 1.115200532012538e-05,
+      "loss": 1.434,
+      "step": 98
+    },
+    {
+      "epoch": 1.5291828793774318,
+      "grad_norm": 13.459453151432884,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.2062,
+      "step": 99
+    },
+    {
+      "epoch": 1.544747081712062,
+      "grad_norm": 6.34554520110176,
+      "learning_rate": 1.0847994679874623e-05,
+      "loss": 1.2515,
+      "step": 100
+    },
+    {
+      "epoch": 1.5603112840466926,
+      "grad_norm": 8.913386857418164,
+      "learning_rate": 1.0696032723048787e-05,
+      "loss": 1.2267,
+      "step": 101
+    },
+    {
+      "epoch": 1.575875486381323,
+      "grad_norm": 9.547469800185302,
+      "learning_rate": 1.0544157480451586e-05,
+      "loss": 1.1735,
+      "step": 102
+    },
+    {
+      "epoch": 1.5914396887159534,
+      "grad_norm": 7.932054956466567,
+      "learning_rate": 1.0392412278274714e-05,
+      "loss": 1.205,
+      "step": 103
+    },
+    {
+      "epoch": 1.6070038910505837,
+      "grad_norm": 9.208669039900636,
+      "learning_rate": 1.02408404056126e-05,
+      "loss": 1.1383,
+      "step": 104
+    },
+    {
+      "epoch": 1.622568093385214,
+      "grad_norm": 7.709935193825099,
+      "learning_rate": 1.0089485102113113e-05,
+      "loss": 1.4121,
+      "step": 105
+    },
+    {
+      "epoch": 1.6381322957198443,
+      "grad_norm": 6.819923905554452,
+      "learning_rate": 9.938389545642388e-06,
+      "loss": 1.3696,
+      "step": 106
+    },
+    {
+      "epoch": 1.6536964980544746,
+      "grad_norm": 8.206400329676246,
+      "learning_rate": 9.787596839967254e-06,
+      "loss": 1.3651,
+      "step": 107
+    },
+    {
+      "epoch": 1.669260700389105,
+      "grad_norm": 10.260363436595911,
+      "learning_rate": 9.637150002458813e-06,
+      "loss": 1.2666,
+      "step": 108
+    },
+    {
+      "epoch": 1.6848249027237354,
+      "grad_norm": 26.767196552606528,
+      "learning_rate": 9.487091951820669e-06,
+      "loss": 1.479,
+      "step": 109
+    },
+    {
+      "epoch": 1.7003891050583657,
+      "grad_norm": 7.51563263665608,
+      "learning_rate": 9.337465495845299e-06,
+      "loss": 1.2219,
+      "step": 110
+    },
+    {
+      "epoch": 1.7159533073929962,
+      "grad_norm": 12.755450160808891,
+      "learning_rate": 9.188313319202057e-06,
+      "loss": 1.4279,
+      "step": 111
+    },
+    {
+      "epoch": 1.7315175097276265,
+      "grad_norm": 6.349610495085197,
+      "learning_rate": 9.039677971260337e-06,
+      "loss": 1.4551,
+      "step": 112
+    },
+    {
+      "epoch": 1.7470817120622568,
+      "grad_norm": 8.917885244170789,
+      "learning_rate": 8.891601853951262e-06,
+      "loss": 1.2766,
+      "step": 113
+    },
+    {
+      "epoch": 1.7626459143968871,
+      "grad_norm": 13.766988130785693,
+      "learning_rate": 8.744127209671516e-06,
+      "loss": 1.2214,
+      "step": 114
+    },
+    {
+      "epoch": 1.7782101167315174,
+      "grad_norm": 15.79931988964264,
+      "learning_rate": 8.597296109232636e-06,
+      "loss": 1.2607,
+      "step": 115
+    },
+    {
+      "epoch": 1.7937743190661477,
+      "grad_norm": 27.982585836161547,
+      "learning_rate": 8.451150439859264e-06,
+      "loss": 1.213,
+      "step": 116
+    },
+    {
+      "epoch": 1.8093385214007782,
+      "grad_norm": 6.366753369802077,
+      "learning_rate": 8.30573189323978e-06,
+      "loss": 1.4226,
+      "step": 117
+    },
+    {
+      "epoch": 1.8249027237354085,
+      "grad_norm": 8.762108357477535,
+      "learning_rate": 8.161081953632701e-06,
+      "loss": 1.2593,
+      "step": 118
+    },
+    {
+      "epoch": 1.840466926070039,
+      "grad_norm": 9.6117893036037,
+      "learning_rate": 8.01724188603228e-06,
+      "loss": 1.625,
+      "step": 119
+    },
+    {
+      "epoch": 1.8560311284046693,
+      "grad_norm": 25.20227315878213,
+      "learning_rate": 7.87425272439662e-06,
+      "loss": 1.7573,
+      "step": 120
+    },
+    {
+      "epoch": 1.8715953307392996,
+      "grad_norm": 18.50697294390281,
+      "learning_rate": 7.732155259941729e-06,
+      "loss": 1.3655,
+      "step": 121
+    },
+    {
+      "epoch": 1.88715953307393,
+      "grad_norm": 11.419496186766294,
+      "learning_rate": 7.590990029504816e-06,
+      "loss": 1.2208,
+      "step": 122
+    },
+    {
+      "epoch": 1.9027237354085602,
+      "grad_norm": 12.960895376933111,
+      "learning_rate": 7.450797303980135e-06,
+      "loss": 1.1531,
+      "step": 123
+    },
+    {
+      "epoch": 1.9182879377431905,
+      "grad_norm": 10.895377744831976,
+      "learning_rate": 7.311617076830715e-06,
+      "loss": 1.2867,
+      "step": 124
+    },
+    {
+      "epoch": 1.933852140077821,
+      "grad_norm": 9.198976531684588,
+      "learning_rate": 7.173489052679236e-06,
+      "loss": 1.3783,
+      "step": 125
+    },
+    {
+      "epoch": 1.9494163424124513,
+      "grad_norm": 7.6941427655967365,
+      "learning_rate": 7.0364526359812924e-06,
+      "loss": 1.5269,
+      "step": 126
+    },
+    {
+      "epoch": 1.9649805447470818,
+      "grad_norm": 7.578325575993518,
+      "learning_rate": 6.900546919784295e-06,
+      "loss": 1.479,
+      "step": 127
+    },
+    {
+      "epoch": 1.9805447470817121,
+      "grad_norm": 9.809861880346132,
+      "learning_rate": 6.7658106745752015e-06,
+      "loss": 1.3796,
+      "step": 128
+    },
+    {
+      "epoch": 1.9961089494163424,
+      "grad_norm": 11.809424540063796,
+      "learning_rate": 6.632282337220272e-06,
+      "loss": 1.8018,
+      "step": 129
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.809424540063796,
+      "learning_rate": 6.500000000000003e-06,
+      "loss": 0.3816,
+      "step": 130
+    },
+    {
+      "epoch": 2.0155642023346303,
+      "grad_norm": 10.863741493343777,
+      "learning_rate": 6.369001399742344e-06,
+      "loss": 1.2037,
+      "step": 131
+    },
+    {
+      "epoch": 2.0311284046692606,
+      "grad_norm": 5.962018084798566,
+      "learning_rate": 6.239323907057342e-06,
+      "loss": 0.9657,
+      "step": 132
+    },
+    {
+      "epoch": 2.046692607003891,
+      "grad_norm": 4.788797901834975,
+      "learning_rate": 6.1110045156762355e-06,
+      "loss": 1.1664,
+      "step": 133
+    },
+    {
+      "epoch": 2.062256809338521,
+      "grad_norm": 6.2976648307960446,
+      "learning_rate": 5.984079831898073e-06,
+      "loss": 1.4275,
+      "step": 134
+    },
+    {
+      "epoch": 2.077821011673152,
+      "grad_norm": 11.390981419662713,
+      "learning_rate": 5.8585860641468674e-06,
+      "loss": 1.1395,
+      "step": 135
+    },
+    {
+      "epoch": 2.093385214007782,
+      "grad_norm": 6.57931364685089,
+      "learning_rate": 5.7345590126422315e-06,
+      "loss": 1.2979,
+      "step": 136
+    },
+    {
+      "epoch": 2.1089494163424125,
+      "grad_norm": 9.124550827147443,
+      "learning_rate": 5.612034059186464e-06,
+      "loss": 1.5149,
+      "step": 137
+    },
+    {
+      "epoch": 2.124513618677043,
+      "grad_norm": 7.9154220919147145,
+      "learning_rate": 5.491046157071034e-06,
+      "loss": 1.2253,
+      "step": 138
+    },
+    {
+      "epoch": 2.140077821011673,
+      "grad_norm": 9.043495071655409,
+      "learning_rate": 5.37162982110527e-06,
+      "loss": 1.2771,
+      "step": 139
+    },
+    {
+      "epoch": 2.1556420233463034,
+      "grad_norm": 7.246287181191101,
+      "learning_rate": 5.253819117770149e-06,
+      "loss": 1.28,
+      "step": 140
+    },
+    {
+      "epoch": 2.1712062256809337,
+      "grad_norm": 14.135867016035936,
+      "learning_rate": 5.137647655500002e-06,
+      "loss": 1.2389,
+      "step": 141
+    },
+    {
+      "epoch": 2.1867704280155644,
+      "grad_norm": 6.191000880702552,
+      "learning_rate": 5.023148575094847e-06,
+      "loss": 1.3685,
+      "step": 142
+    },
+    {
+      "epoch": 2.2023346303501947,
+      "grad_norm": 6.912497051747966,
+      "learning_rate": 4.910354540266184e-06,
+      "loss": 1.1248,
+      "step": 143
+    },
+    {
+      "epoch": 2.217898832684825,
+      "grad_norm": 7.634399054473615,
+      "learning_rate": 4.799297728318821e-06,
+      "loss": 1.2091,
+      "step": 144
+    },
+    {
+      "epoch": 2.2334630350194553,
+      "grad_norm": 8.654404179498275,
+      "learning_rate": 4.690009820971527e-06,
+      "loss": 1.2775,
+      "step": 145
+    },
+    {
+      "epoch": 2.2490272373540856,
+      "grad_norm": 5.486520320319506,
+      "learning_rate": 4.582521995319019e-06,
+      "loss": 1.3234,
+      "step": 146
+    },
+    {
+      "epoch": 2.264591439688716,
+      "grad_norm": 14.08610341346389,
+      "learning_rate": 4.476864914937923e-06,
+      "loss": 1.1865,
+      "step": 147
+    },
+    {
+      "epoch": 2.280155642023346,
+      "grad_norm": 11.693098373701448,
+      "learning_rate": 4.373068721139227e-06,
+      "loss": 1.4238,
+      "step": 148
+    },
+    {
+      "epoch": 2.2957198443579765,
+      "grad_norm": 9.49971316853895,
+      "learning_rate": 4.271163024369722e-06,
+      "loss": 1.1235,
+      "step": 149
+    },
+    {
+      "epoch": 2.311284046692607,
+      "grad_norm": 7.887870435405849,
+      "learning_rate": 4.171176895764882e-06,
+      "loss": 1.1697,
+      "step": 150
+    },
+    {
+      "epoch": 2.3268482490272375,
+      "grad_norm": 7.29104535243051,
+      "learning_rate": 4.07313885885561e-06,
+      "loss": 1.4309,
+      "step": 151
+    },
+    {
+      "epoch": 2.342412451361868,
+      "grad_norm": 10.320755505362524,
+      "learning_rate": 3.977076881431175e-06,
+      "loss": 1.3613,
+      "step": 152
+    },
+    {
+      "epoch": 2.357976653696498,
+      "grad_norm": 5.857317648653641,
+      "learning_rate": 3.883018367560715e-06,
+      "loss": 1.3462,
+      "step": 153
+    },
+    {
+      "epoch": 2.3735408560311284,
+      "grad_norm": 9.13512553833875,
+      "learning_rate": 3.7909901497755408e-06,
+      "loss": 1.3862,
+      "step": 154
+    },
+    {
+      "epoch": 2.3891050583657587,
+      "grad_norm": 6.878082659822421,
+      "learning_rate": 3.7010184814144916e-06,
+      "loss": 1.3616,
+      "step": 155
+    },
+    {
+      "epoch": 2.404669260700389,
+      "grad_norm": 5.910003013217337,
+      "learning_rate": 3.6131290291345155e-06,
+      "loss": 1.3136,
+      "step": 156
+    },
+    {
+      "epoch": 2.4202334630350193,
+      "grad_norm": 9.041793350178478,
+      "learning_rate": 3.527346865588614e-06,
+      "loss": 1.2654,
+      "step": 157
+    },
+    {
+      "epoch": 2.43579766536965,
+      "grad_norm": 9.955462288729418,
+      "learning_rate": 3.4436964622732493e-06,
+      "loss": 1.3949,
+      "step": 158
+    },
+    {
+      "epoch": 2.4513618677042803,
+      "grad_norm": 12.124015441070618,
+      "learning_rate": 3.3622016825472414e-06,
+      "loss": 1.3149,
+      "step": 159
+    },
+    {
+      "epoch": 2.4669260700389106,
+      "grad_norm": 5.944228819887684,
+      "learning_rate": 3.2828857748241404e-06,
+      "loss": 1.3735,
+      "step": 160
+    },
+    {
+      "epoch": 2.482490272373541,
+      "grad_norm": 7.465704659945909,
+      "learning_rate": 3.205771365940052e-06,
+      "loss": 1.1572,
+      "step": 161
+    },
+    {
+      "epoch": 2.498054474708171,
+      "grad_norm": 8.012935003044838,
+      "learning_rate": 3.1308804546987615e-06,
+      "loss": 1.2964,
+      "step": 162
+    },
+    {
+      "epoch": 2.5136186770428015,
+      "grad_norm": 6.396153961978255,
+      "learning_rate": 3.058234405596029e-06,
+      "loss": 1.2518,
+      "step": 163
+    },
+    {
+      "epoch": 2.529182879377432,
+      "grad_norm": 32.66960667166894,
+      "learning_rate": 2.9878539427248364e-06,
+      "loss": 1.3154,
+      "step": 164
+    },
+    {
+      "epoch": 2.544747081712062,
+      "grad_norm": 7.182443079061496,
+      "learning_rate": 2.919759143863326e-06,
+      "loss": 1.2754,
+      "step": 165
+    },
+    {
+      "epoch": 2.5603112840466924,
+      "grad_norm": 9.065894651134005,
+      "learning_rate": 2.8539694347471093e-06,
+      "loss": 1.5717,
+      "step": 166
+    },
+    {
+      "epoch": 2.5758754863813227,
+      "grad_norm": 8.155108121011244,
+      "learning_rate": 2.7905035835276e-06,
+      "loss": 1.1931,
+      "step": 167
+    },
+    {
+      "epoch": 2.5914396887159534,
+      "grad_norm": 10.525703817651328,
+      "learning_rate": 2.7293796954179254e-06,
+      "loss": 1.2438,
+      "step": 168
+    },
+    {
+      "epoch": 2.6070038910505837,
+      "grad_norm": 10.790702057048689,
+      "learning_rate": 2.670615207527965e-06,
+      "loss": 1.2728,
+      "step": 169
+    },
+    {
+      "epoch": 2.622568093385214,
+      "grad_norm": 6.486978399127539,
+      "learning_rate": 2.6142268838899844e-06,
+      "loss": 1.3483,
+      "step": 170
+    },
+    {
+      "epoch": 2.6381322957198443,
+      "grad_norm": 11.399298263764798,
+      "learning_rate": 2.5602308106762773e-06,
+      "loss": 1.4894,
+      "step": 171
+    },
+    {
+      "epoch": 2.6536964980544746,
+      "grad_norm": 8.803157004201939,
+      "learning_rate": 2.5086423916101794e-06,
+      "loss": 1.5442,
+      "step": 172
+    },
+    {
+      "epoch": 2.669260700389105,
+      "grad_norm": 7.898925628777204,
+      "learning_rate": 2.4594763435717788e-06,
+      "loss": 1.3132,
+      "step": 173
+    },
+    {
+      "epoch": 2.6848249027237356,
+      "grad_norm": 6.01024097821099,
+      "learning_rate": 2.412746692399561e-06,
+      "loss": 1.3329,
+      "step": 174
+    },
+    {
+      "epoch": 2.700389105058366,
+      "grad_norm": 9.287448544998288,
+      "learning_rate": 2.3684667688891813e-06,
+      "loss": 1.2279,
+      "step": 175
+    },
+    {
+      "epoch": 2.7159533073929962,
+      "grad_norm": 6.509435104920216,
+      "learning_rate": 2.3266492049905327e-06,
+      "loss": 1.1356,
+      "step": 176
+    },
+    {
+      "epoch": 2.7315175097276265,
+      "grad_norm": 7.274526660218056,
+      "learning_rate": 2.2873059302041627e-06,
+      "loss": 1.2053,
+      "step": 177
+    },
+    {
+      "epoch": 2.747081712062257,
+      "grad_norm": 7.528171905726772,
+      "learning_rate": 2.250448168178085e-06,
+      "loss": 1.2631,
+      "step": 178
+    },
+    {
+      "epoch": 2.762645914396887,
+      "grad_norm": 7.685404987229149,
+      "learning_rate": 2.216086433505963e-06,
+      "loss": 1.1471,
+      "step": 179
+    },
+    {
+      "epoch": 2.7782101167315174,
+      "grad_norm": 7.30724911654224,
+      "learning_rate": 2.18423052872755e-06,
+      "loss": 1.1335,
+      "step": 180
+    },
+    {
+      "epoch": 2.7937743190661477,
+      "grad_norm": 8.275377130204019,
+      "learning_rate": 2.154889541532279e-06,
+      "loss": 1.4331,
+      "step": 181
+    },
+    {
+      "epoch": 2.809338521400778,
+      "grad_norm": 8.26916689050228,
+      "learning_rate": 2.128071842166766e-06,
+      "loss": 1.1323,
+      "step": 182
+    },
+    {
+      "epoch": 2.8249027237354083,
+      "grad_norm": 8.648891670292945,
+      "learning_rate": 2.1037850810469977e-06,
+      "loss": 1.0748,
+      "step": 183
+    },
+    {
+      "epoch": 2.840466926070039,
+      "grad_norm": 8.864628121919203,
+      "learning_rate": 2.0820361865758506e-06,
+      "loss": 1.2159,
+      "step": 184
+    },
+    {
+      "epoch": 2.8560311284046693,
+      "grad_norm": 7.550747013009374,
+      "learning_rate": 2.0628313631665977e-06,
+      "loss": 1.1746,
+      "step": 185
+    },
+    {
+      "epoch": 2.8715953307392996,
+      "grad_norm": 5.4396609218382075,
+      "learning_rate": 2.0461760894729438e-06,
+      "loss": 1.1403,
+      "step": 186
+    },
+    {
+      "epoch": 2.88715953307393,
+      "grad_norm": 9.061879291284523,
+      "learning_rate": 2.032075116826103e-06,
+      "loss": 1.5448,
+      "step": 187
+    },
+    {
+      "epoch": 2.90272373540856,
+      "grad_norm": 6.124913133747852,
+      "learning_rate": 2.0205324678793635e-06,
+      "loss": 1.1864,
+      "step": 188
+    },
+    {
+      "epoch": 2.9182879377431905,
+      "grad_norm": 7.03064717545691,
+      "learning_rate": 2.0115514354605255e-06,
+      "loss": 1.3855,
+      "step": 189
+    },
+    {
+      "epoch": 2.9338521400778212,
+      "grad_norm": 8.91521754504974,
+      "learning_rate": 2.005134581632538e-06,
+      "loss": 1.3689,
+      "step": 190
+    },
+    {
+      "epoch": 2.9494163424124515,
+      "grad_norm": 8.561228532947991,
+      "learning_rate": 2.001283736962612e-06,
+      "loss": 1.5862,
+      "step": 191
+    },
+    {
+      "epoch": 2.964980544747082,
+      "grad_norm": 10.281179103024385,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1926,
+      "step": 192
+    },
+    {
+      "epoch": 2.964980544747082,
+      "step": 192,
+      "total_flos": 104900150247424.0,
+      "train_loss": 1.356536865234375,
+      "train_runtime": 15762.2393,
+      "train_samples_per_second": 1.571,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 104900150247424.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1918653a3fe98035d9d4a6e177922572597ce089b52b5f1b9a5e3a61b94650ca
+size 8120