Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,51 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_calls>": 151670,
+  "</tool_response>": 151666,
+  "<dream>": 151682,
+  "<dream_end>": 151684,
+  "<dream_start>": 151683,
+  "<im_end>": 151681,
+  "<im_patch>": 151679,
+  "<im_start>": 151680,
+  "<patch_end>": 151690,
+  "<patch_newline>": 151691,
+  "<patch_start>": 151689,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_calls>": 151669,
+  "<tool_response>": 151665,
+  "<video_end>": 151688,
+  "<video_start>": 151687,
+  "<|BOT|>": 151672,
+  "<|CALL_END|>": 151674,
+  "<|CALL_START|>": 151673,
+  "<|EOT|>": 151671,
+  "<|IMG_END|>": 151678,
+  "<|IMG_START|>": 151677,
+  "<|MASK_1e69f|>": 151685,
+  "<|THINK_END|>": 151676,
+  "<|THINK_START|>": 151675,
+  "<|UNMASK_1e69f|>": 151686,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,81 @@
+{% macro render_content(content) %}{% if content is none %}{{- '' }}{% elif content is string %}{{- content }}{% elif content is mapping %}{{- content['value'] if 'value' in content else content['text'] }}{% elif content is iterable %}{% for item in content %}{% if item.type == 'text' %}{{- item['value'] if 'value' in item else item['text'] }}{% elif item.type == 'image' %}<im_patch>{% endif %}{% endfor %}{% endif %}{% endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content) + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nAlways adhere to this exact format for tool use:\n<tool_calls>\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n{additional_tool_calls}</tool_calls>\n\nNote:\n- For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags.\n- `<function-name>` must be an exact match to one of the available tools.\n- `<args-json-object>` must be valid JSON that strictly follows the tool's parameters schema.<|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + render_content(messages[0].content) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and render_content(message.content) is string and not(render_content(message.content).startswith('<tool_response>') and render_content(message.content).endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {%- set role_name = 'observation' if (message.role == "system" and not loop.first and message.name == 'observation') else message.role %}
+        {{- '<|im_start|>' + role_name + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = render_content(message.reasoning_content) %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- else %}
+                {%- set reasoning_content = '' %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {{- '\n<tool_calls>' }}
+            {%- for tool_call in message.tool_calls %}
+                {{- '\n' }}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+            {{- '\n</tool_calls>' }}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>tool_response' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,67 @@
+{
+    "architectures": [
+        "MMGPTStepRoboticsForCausalLM"
+    ],
+    "auto_map": {
+        "AutoConfig": "configuration_step_robotics.StepRoboticsConfig",
+        "AutoModel": "modeling_step_robotics.MMGPTStepRoboticsForCausalLM"
+    },
+    "model_type": "step_robotics",
+    "im_end_token": "<im_end>",
+    "im_patch_token": "<im_patch>",
+    "im_start_token": "<im_start>",
+    "image_token_len": 169,
+    "patch_token_len": 81,
+    "image_token_id": 151679,
+    "understand_projector_stride": 2,
+    "use_im_start_end": "true",
+    "vision_select_layer": -1,
+    "projector_bias": false,
+    "vision_config": {
+        "model_type": "perception_encoder",
+        "image_size": 728,
+        "patch_size": 14,
+        "width": 1536,
+        "layers": 47,
+        "heads": 16,
+        "pool_type": "none",
+        "output_dim": null,
+        "use_cls_token": false,
+        "ls_init_value": 0.1,
+        "use_ln_post": false,
+        "hidden_act": "quick_gelu"
+    },
+    "text_config": {
+        "architectures": [
+            "Qwen3ForCausalLM"
+        ],
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "bos_token_id": 151643,
+        "eos_token_id": [
+            151643,
+            151679
+        ],
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "initializer_range": 0.02,
+        "intermediate_size": 12288,
+        "max_position_embeddings": 40960,
+        "max_window_layers": 36,
+        "model_type": "qwen3",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 36,
+        "num_key_value_heads": 8,
+        "rms_norm_eps": 1e-06,
+        "rope_scaling": null,
+        "rope_theta": 1000000,
+        "sliding_window": null,
+        "tie_word_embeddings": false,
+        "torch_dtype": "bfloat16",
+        "transformers_version": "4.51.0",
+        "use_cache": true,
+        "use_sliding_window": false,
+        "vocab_size": 151936
+    }
+}

configuration_step_robotics.py

@@ -0,0 +1,100 @@
+from typing import Any, Optional, Union
+from transformers.configuration_utils import PretrainedConfig
+from transformers.models.qwen3 import Qwen3Config
+from transformers import logging
+import os
+
+logger = logging.get_logger(__name__)
+
+
+class PerceptionEncoderConfig(PretrainedConfig):
+    model_type = "perception_encoder"
+
+    def __init__(self,
+        patch_size: int = 14,
+        width: int = 1024,
+        layers: int = 23,
+        heads: int = 16,
+        mlp_ratio: float = 8960 / 1536,
+        output_dim: Optional[int] = None,
+        ls_init_value: float = None,
+        drop_path: float = 0.0,
+        image_size: int = 448,
+        use_abs_posemb: bool = True,
+        use_cls_token: bool = False,
+        use_rope2d: bool = True,
+        pool_type: str = "attn",
+        attn_pooler_heads: int = 8,
+        use_ln_pre: bool = True,
+        use_ln_post: bool = True,
+        **kwargs):
+        super().__init__(**kwargs)
+
+        self.patch_size=patch_size
+        self.width=width
+        self.layers=layers
+        self.heads=heads
+        self.mlp_ratio=mlp_ratio
+        self.output_dim=output_dim
+        self.ls_init_value=ls_init_value
+        self.drop_path=drop_path
+        self.image_size=image_size
+        self.use_abs_posemb=use_abs_posemb
+        self.use_cls_token=use_cls_token
+        self.use_rope2d=use_rope2d
+        self.pool_type=pool_type
+        self.attn_pooler_heads=attn_pooler_heads
+        self.use_ln_pre=use_ln_pre
+        self.use_ln_post=use_ln_post
+    
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        if 'vision_tower_config' in config_dict:
+            config_dict = config_dict['vision_tower_config']
+
+        if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)
+
+
+class StepRoboticsConfig(PretrainedConfig):
+    model_type = "step_robotics"
+
+    def __init__(
+        self,
+        vision_config: Optional[Union[dict, PerceptionEncoderConfig]] = None,
+        text_config: Optional[Union[dict, Qwen3Config]] = None,
+        understand_projector_stride: int = 1,
+        projector_bias: bool = True,
+        image_token_id: int = 151675,
+        **kwargs,
+    ) -> None:
+        if vision_config is None:
+            vision_config = PerceptionEncoderConfig()
+        elif isinstance(vision_config, dict):
+            vision_config = PerceptionEncoderConfig(**vision_config)
+        self.vision_tower_config = vision_config
+
+        if text_config is None:
+            text_config = Qwen3Config()
+        elif isinstance(text_config, dict):
+            text_config = Qwen3Config(**text_config)
+        self.text_config = text_config
+
+        self.understand_projector_stride = understand_projector_stride
+        self.projector_bias = projector_bias
+        self.hidden_size = text_config.hidden_size
+        self.image_token_id = image_token_id
+
+        super().__init__(**kwargs)
+
+if __name__ == "__main__":
+    from transformers import AutoConfig
+    stepR = "/data/project/step_encoder/vllm/vllm/step_robotics"
+    config = AutoConfig.from_pretrained(stepR, trust_remote_code=True)

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5893c3b86be2ff438729fa4481fa965068e015cfee9ba3d12f2729ccb9ff9b
+size 4286778640

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159c14a2cf7a240919495a4bacf5e3d7419535a7f13cb04f6ed7b51f486b36a0
+size 4286779488

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd8b4722ddb760ddb5de6f497366f41fa8fb7e6b091b279dbb351b31c8ad33e
+size 4244835480

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02704aac98933248462eb0ae78fd2afc8b776e10ff0edae8cfc406990491e77a
+size 4270911400

model-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024b0312794a5a6e0e95acc97b91a13e2ead4a1f5da6e4158a5014854f30e370
+size 3254325800

model.safetensors.index.json

@@ -0,0 +1,1071 @@
+{
+    "metadata": {},
+    "weight_map": {
+        "model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model-00001.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model-00001.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model-00002.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.32.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.32.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.33.self_attn.q_norm.weight": "model-00003.safetensors",
+        "model.layers.33.self_attn.k_norm.weight": "model-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004.safetensors",
+        "model.layers.34.self_attn.q_norm.weight": "model-00004.safetensors",
+        "model.layers.34.self_attn.k_norm.weight": "model-00004.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00004.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00004.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00004.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00004.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00004.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00004.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00004.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00004.safetensors",
+        "model.layers.35.self_attn.q_norm.weight": "model-00004.safetensors",
+        "model.layers.35.self_attn.k_norm.weight": "model-00004.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00004.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00004.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00004.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00004.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00004.safetensors",
+        "model.embed_tokens.weight": "model-00004.safetensors",
+        "vision_model.positional_embedding": "model-00004.safetensors",
+        "vision_model.conv1.weight": "model-00004.safetensors",
+        "vision_model.ln_pre.weight": "model-00004.safetensors",
+        "vision_model.ln_pre.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.0.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.1.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.2.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.3.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.4.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.5.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.6.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.7.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.8.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.9.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.10.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.11.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.12.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.13.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.14.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.15.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.16.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.17.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.18.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.19.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.20.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.21.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.22.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.23.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.24.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.mlp.c_fc.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.mlp.c_fc.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.mlp.c_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.25.mlp.c_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.attn.in_proj_weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.attn.in_proj_bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.attn.out_proj.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.attn.out_proj.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.ls_1.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.ls_2.gamma": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.ln_1.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.ln_1.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.ln_2.weight": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.ln_2.bias": "model-00004.safetensors",
+        "vision_model.transformer.resblocks.26.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.26.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.26.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.26.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.27.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.28.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.29.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.30.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.31.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.32.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.33.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.34.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.35.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.36.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.37.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.38.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.39.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.40.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.41.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.42.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.43.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.44.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.45.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.attn.in_proj_weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.attn.in_proj_bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.attn.out_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.attn.out_proj.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.ls_1.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.ls_2.gamma": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.ln_1.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.ln_1.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.ln_2.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.ln_2.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.mlp.c_fc.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.mlp.c_fc.bias": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.mlp.c_proj.weight": "model-00005.safetensors",
+        "vision_model.transformer.resblocks.46.mlp.c_proj.bias": "model-00005.safetensors",
+        "vision_model.vit_downsampler1.weight": "model-00005.safetensors",
+        "vision_model.vit_downsampler1.bias": "model-00005.safetensors",
+        "vision_model.vit_downsampler2.weight": "model-00005.safetensors",
+        "vision_model.vit_downsampler2.bias": "model-00005.safetensors",
+        "vit_large_projector.weight": "model-00005.safetensors",
+        "model.norm.weight": "model-00005.safetensors",
+        "lm_head.weight": "model-00005.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,270 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<tool_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tool_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|BOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|CALL_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|CALL_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|THINK_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|THINK_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|IMG_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|IMG_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<im_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<im_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<im_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<dream>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<dream_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<dream_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|MASK_1e69f|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|UNMASK_1e69f|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<video_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<video_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<patch_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<patch_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<patch_newline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439885437ceee7205faa72b808b543bb3fcd2f3df788a959aa3604d07a8f5c75
+size 11426994

tokenizer_config.json

@@ -0,0 +1,446 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<tool_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "</tool_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|BOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|CALL_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|CALL_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|THINK_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151676": {
+      "content": "<|THINK_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<|IMG_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<|IMG_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<im_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<im_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<im_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<dream>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<dream_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<dream_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<|MASK_1e69f|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<|UNMASK_1e69f|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<video_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<video_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<patch_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<patch_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<patch_newline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<tool_calls>",
+    "</tool_calls>",
+    "<|EOT|>",
+    "<|BOT|>",
+    "<|CALL_START|>",
+    "<|CALL_END|>",
+    "<|THINK_START|>",
+    "<|THINK_END|>",
+    "<|IMG_START|>",
+    "<|IMG_END|>",
+    "<im_patch>",
+    "<im_start>",
+    "<im_end>",
+    "<dream>",
+    "<dream_start>",
+    "<dream_end>",
+    "<|MASK_1e69f|>",
+    "<|UNMASK_1e69f|>",
+    "<video_start>",
+    "<video_end>",
+    "<patch_start>",
+    "<patch_end>",
+    "<patch_newline>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}