Upload EMOVAForConditionalGeneration

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "D:\\temp\\emova_data\\checkpoints\\emova_qwen2_5_3b",
+  "architectures": [
+    "EMOVAForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_emova.EMOVAConfig",
+    "AutoModel": "modeling_emova.EMOVAForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_emova.EMOVAForConditionalGeneration"
+  },
+  "default_system_prompt": "You are a helpful assistant.",
+  "ignore_index": -100,
+  "image_token_index": 155761,
+  "mm_projector_config": {
+    "mlp_depth": 2,
+    "trainable": true,
+    "type": "MLPProjector"
+  },
+  "model_type": "emova",
+  "text_config": {
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_size": 2048,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 2,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "float32",
+    "use_sliding_window": false,
+    "vocab_size": 155776
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "max_pixels": 3211264,
+    "model_type": "qwen2_vl",
+    "pretrained_model_name_or_path": "Emova-ollm/qwen2vit600m",
+    "trainable": true,
+    "type": "Qwen2VisionTower",
+    "unfreeze_mm_vision_tower": true
+  }
+}

configuration_emova.py

@@ -0,0 +1,160 @@
+# coding=utf-8
+# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""EMOVA model configuration"""
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+from transformers.models.auto import CONFIG_MAPPING
+
+from .configuration_qwen2vit import Qwen2VLVisionConfig
+
+logger = logging.get_logger(__name__)
+
+
+class EMOVAConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`EMOVAForConditionalGeneration`]. It is used to instantiate an
+    EMOVA model according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        vision_config (`Union[AutoConfig, dict]`,  *optional*, defaults to `CLIPVisionConfig`):
+            The config object or dictionary of the vision backbone.
+        text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`):
+            The config object or dictionary of the text backbone.
+        ignore_index (`int`, *optional*, defaults to -100):
+            The ignore index for the loss function.
+        image_token_index (`int`, *optional*, defaults to 32000):
+            The image token index to encode the image prompt.
+        projector_hidden_act (`str`, *optional*, defaults to `"gelu"`):
+            The activation function used by the multimodal projector.
+        vision_feature_select_strategy (`str`, *optional*, defaults to `"default"`):
+            The feature selection strategy used to select the vision feature from the vision backbone.
+            Can be one of `"default"` or `"full"`. If `"default"`, the CLS token is removed from the vision features.
+            If `"full"`, the full vision features are used.
+        vision_feature_layer (`int`, *optional*, defaults to -2):
+            The index of the layer to select the vision feature.
+        image_grid_pinpoints (`List`, *optional*, defaults to `[[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]]`):
+            A list of possible resolutions to use for processing high resolution images. Each item in the list should be a tuple or list
+            of the form `(height, width)`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+
+    Example:
+
+    ```python
+    >>> from transformers import EMOVAForConditionalGeneration, EMOVAConfig, CLIPVisionConfig, LlamaConfig
+
+    >>> # Initializing a CLIP-vision config
+    >>> vision_config = CLIPVisionConfig()
+
+    >>> # Initializing a Llama config
+    >>> text_config = LlamaConfig()
+
+    >>> # Initializing a EMOVA style configuration
+    >>> configuration = EMOVAConfig(vision_config, text_config)
+
+    >>> # Initializing a model from the style configuration
+    >>> model = EMOVAForConditionalGeneration(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "emova"
+    is_composition = False
+
+    def __init__(
+            self,
+            vision_config=None,
+            mm_projector_config=None,
+            text_config=None,
+            ignore_index=-100,
+            image_token_index=32000,
+            vision_feature_select_strategy="default",
+            vision_feature_layer=-2,
+            is_native_resolution=True,
+            image_grid_pinpoints=None,
+            use_image_newline_parameter=False,
+            tie_word_embeddings=False,
+            **kwargs,
+    ):
+        self.ignore_index = ignore_index
+        self.image_token_index = image_token_index
+
+        if vision_feature_select_strategy not in ["default", "full"]:
+            raise ValueError(
+                "vision_feature_select_strategy should be one of 'default', 'full'."
+                f"Got: {vision_feature_select_strategy}"
+            )
+
+        # self.vision_feature_select_strategy = vision_feature_select_strategy
+        # self.vision_feature_layer = vision_feature_layer
+        # image_grid_pinpoints = (
+        #     image_grid_pinpoints
+        #     if image_grid_pinpoints is not None
+        #     else [[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]]
+        # )
+        # self.is_native_resolution = is_native_resolution
+        # self.image_grid_pinpoints = image_grid_pinpoints if not self.is_native_resolution else None
+        # self.use_image_newline_parameter = use_image_newline_parameter
+
+        if isinstance(vision_config, dict):
+            vision_config = Qwen2VLVisionConfig(**vision_config)
+        elif vision_config is None:
+            vision_config = Qwen2VLVisionConfig(
+                depth=32,
+                embed_dim=1280,
+                hidden_act="quick_gelu",
+                hidden_size=3584,
+                in_channels=3,
+                in_chans=3,
+                mlp_ratio=4,
+                model_type="qwen2_vl",
+                num_heads=16,
+                patch_size=14,
+                spatial_merge_size=2,
+                spatial_patch_size=14,
+                temporal_patch_size=2,
+                initializer_range=0.02,
+            )
+
+        # if isinstance(vision_config, dict):
+        #     vision_config["model_type"] = (
+        #         vision_config["model_type"] if "model_type" in vision_config else "clip_vision_model"
+        #     )
+        #     vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config)
+        # elif vision_config is None:
+        #     vision_config = CONFIG_MAPPING["clip_vision_model"](
+        #         intermediate_size=4096,
+        #         hidden_size=1024,
+        #         patch_size=14,
+        #         image_size=336,
+        #         num_hidden_layers=24,
+        #         num_attention_heads=16,
+        #         vocab_size=32000,
+        #         projection_dim=768,
+        #     )
+
+        self.vision_config = vision_config
+        self.mm_projector_config = mm_projector_config
+        if isinstance(text_config, dict):
+            text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "llama"
+            text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
+        elif text_config is None:
+            text_config = CONFIG_MAPPING["llama"]()
+
+        self.text_config = text_config
+        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)

configuration_qwen2vit.py

@@ -0,0 +1,71 @@
+# coding=utf-8
+# Copyright 2024 The Qwen team, Alibaba Group and the HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Qwen2VL model configuration"""
+
+import os
+from typing import Union
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class Qwen2VLVisionConfig(PretrainedConfig):
+    model_type = "qwen2_vl"
+
+    def __init__(
+            self,
+            depth=32,
+            embed_dim=1280,
+            hidden_size=3584,
+            hidden_act="quick_gelu",
+            mlp_ratio=4,
+            num_heads=16,
+            in_channels=3,
+            patch_size=14,
+            spatial_merge_size=2,
+            temporal_patch_size=2,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.depth = depth
+        self.embed_dim = embed_dim
+        self.hidden_size = hidden_size
+        self.hidden_act = hidden_act
+        self.mlp_ratio = mlp_ratio
+        self.num_heads = num_heads
+        self.in_channels = in_channels
+        self.patch_size = patch_size
+        self.spatial_merge_size = spatial_merge_size
+        self.temporal_patch_size = temporal_patch_size
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
+        cls._set_token_in_kwargs(kwargs)
+
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        # if config_dict.get("model_type") == "qwen2_vl":
+        #     config_dict = config_dict["vision_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)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.47.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8675a1c5f604daf475d28146a1a0f5be0e6d2557897576a1cb21285716bffe42
+size 4960533152

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a10907bcd061d46caf462a05fa51b316d7d3d4ec31d4d7aaf0b4e6f231fe32e
+size 2601767944

model.safetensors.index.json

@@ -0,0 +1,836 @@
+{
+  "metadata": {
+    "total_size": 7562201088
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.0.bias": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.0.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.2.bias": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.ln_q.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}