Upload 12 files

README.md

@@ -0,0 +1,24 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- llava
+- multimodal
+- qwen
+- mlx
+---
+
+# mlx-community/nanoLLaVA
+This model was converted to MLX format from [`qnguyen3/nanoLLaVA`]() using mlx-vllm version **0.0.0**.
+Refer to the [original model card](https://huggingface.co/qnguyen3/nanoLLaVA) for more details on the model.
+## Use with mlx
+
+```bash
+git clone https://github.com/ml-explore/mlx-examples.git
+```
+
+```bash
+cd mlx-lm/vllms
+python -m generate --model mlx_model --max-tokens 10 --temp 0.0
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,197 @@
+{
+    "architectures": [
+        "LlavaQwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_llava_qwen2.LlavaQwen2Config",
+        "AutoModelForCausalLM": "modeling_llava_qwen2.LlavaQwen2ForCausalLM"
+    },
+    "bos_token_id": 151645,
+    "eos_token_id": 151645,
+    "freeze_mm_mlp_adapter": false,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_aspect_ratio": "pad",
+    "initializer_range": 0.02,
+    "intermediate_size": 2816,
+    "language_model": "vilm/Quyen-SE-v0.1",
+    "max_position_embeddings": 32768,
+    "max_window_layers": 21,
+    "mm_hidden_size": 1152,
+    "mm_projector_lr": null,
+    "mm_projector_type": "mlp2x_gelu",
+    "mm_vision_tower": "google/siglip-so400m-patch14-384",
+    "model_type": "llava-qwen2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 4096,
+    "text_config": {
+        "vocab_size": 151936,
+        "max_position_embeddings": 32768,
+        "hidden_size": 1024,
+        "intermediate_size": 2816,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "use_sliding_window": false,
+        "sliding_window": 4096,
+        "max_window_layers": 21,
+        "num_key_value_heads": 16,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-06,
+        "use_cache": false,
+        "rope_theta": 1000000.0,
+        "attention_dropout": 0.0,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": false,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": [
+            "Qwen2ForCausalLM"
+        ],
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": 151645,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "vilm/Quyen-SE-v0.1",
+        "transformers_version": "4.39.3",
+        "model_type": "qwen2"
+    },
+    "tie_word_embeddings": false,
+    "tokenizer_model_max_length": 4096,
+    "tokenizer_padding_side": "right",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.2",
+    "tune_mm_mlp_adapter": false,
+    "use_cache": false,
+    "use_mm_proj": true,
+    "use_sliding_window": false,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "model_type": "siglip_vision_model",
+        "hidden_size": 1152,
+        "intermediate_size": 4304,
+        "num_hidden_layers": 27,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 14,
+        "image_size": 384,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "gelu_pytorch_tanh"
+    },
+    "vocab_size": 151936
+}

configuration_llava_qwen2.py

@@ -0,0 +1,202 @@
+# 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.
+""" Qwen2 model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+QWEN2_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "Qwen/Qwen2-7B-beta": "https://huggingface.co/Qwen/Qwen2-7B-beta/resolve/main/config.json",
+}
+
+
+class Qwen2Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Qwen2Model`]. It is used to instantiate a
+    Qwen2 model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of
+    Qwen2-7B-beta [Qwen/Qwen2-7B-beta](https://huggingface.co/Qwen/Qwen2-7B-beta).
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 151936):
+            Vocabulary size of the Qwen2 model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Qwen2Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 22016):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 32):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 32768):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 28):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import Qwen2Model, Qwen2Config
+
+    >>> # Initializing a Qwen2 style configuration
+    >>> configuration = Qwen2Config()
+
+    >>> # Initializing a model from the Qwen2-7B style configuration
+    >>> model = Qwen2Model(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "qwen2"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=151936,
+        hidden_size=4096,
+        intermediate_size=22016,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=32,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window
+        self.max_window_layers = max_window_layers
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+from typing import Union
+from transformers import PretrainedConfig
+import os
+
+
+class SigLipVisionConfig(PretrainedConfig):
+    model_type = "siglip_vision_model"
+
+    def __init__(
+            self,
+            hidden_size=1152,
+            image_mean=(0.5, 0.5, 0.5),
+            intermediate_size=4304,
+            num_hidden_layers=27,
+            num_attention_heads=16,
+            num_channels=3,
+            image_size=384,
+            patch_size=14,
+            hidden_act="gelu_pytorch_tanh",
+            layer_norm_eps=1e-6,
+            attention_dropout=0.0,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.attention_dropout = attention_dropout
+        self.layer_norm_eps = layer_norm_eps
+        self.hidden_act = hidden_act
+        self.image_mean = image_mean
+
+    @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)
+
+        # get the vision config dict if we are loading from SigLipConfig
+        if config_dict.get("model_type") == "siglip":
+            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)
+
+class LlavaQwen2Config(Qwen2Config):
+    model_type = "llava-qwen2"

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b121b46cd2a831f9c653fd791eff889413f42ff69748249679ff1ed7efe3d582
+size 2100156290

model.safetensors.index.json

@@ -0,0 +1,750 @@
+{
+    "metadata": {
+        "total_size": 2100052096
+    },
+    "weight_map": {
+        "language_model.model.embed_tokens.weight": "model.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.lm_head.weight": "model.safetensors",
+        "language_model.model.norm.weight": "model.safetensors",
+        "mm_projector.linear_1.bias": "model.safetensors",
+        "mm_projector.linear_1.weight": "model.safetensors",
+        "mm_projector.linear_2.bias": "model.safetensors",
+        "mm_projector.linear_2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.attention.in_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.attention.in_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.attention.out_proj.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.attention.out_proj.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.layernorm.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.layernorm.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.mlp.fc1.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.mlp.fc1.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.mlp.fc2.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.mlp.fc2.weight": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.head.probe": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.post_layernorm.bias": "model.safetensors",
+        "vision_tower.vision_tower.vision_model.post_layernorm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_end|>",
+    "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_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nAnswer the questions.<|im_end|>' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}