Upload CenturioForConditionalGeneration

config.json

@@ -0,0 +1,104 @@
+{
+  "_name_or_path": "centurio_aya",
+  "adapter_config": {
+    "adapter_multi_scale": 2
+  },
+  "adapter_type": "multiscale-pool",
+  "architectures": [
+    "CenturioForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_centurio.CenturioConfig",
+    "AutoModelForCausalLM": "modeling_centurio.CenturioForConditionalGeneration"
+  },
+  "ignore_index": -100,
+  "image_hidden_size": 1152,
+  "image_token_index": 255029,
+  "model_type": "centurio",
+  "text_config": {
+    "_name_or_path": "CohereForAI/aya-expanse-8b",
+    "add_cross_attention": false,
+    "architectures": [
+      "CohereForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 5,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 255001,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "logit_scale": 0.125,
+    "max_length": 20,
+    "max_position_embeddings": 8192,
+    "min_length": 0,
+    "model_type": "cohere",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_qk_norm": false,
+    "vocab_size": 256000
+  },
+  "timm_model": "vit_so400m_patch14_siglip_384",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "vision_config": {}
+}

configuration_centurio.py

@@ -0,0 +1,78 @@
+# coding=utf-8
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers import logging, AutoConfig
+from transformers import CONFIG_MAPPING
+
+
+logger = logging.get_logger(__name__)
+
+
+class CenturioConfig(PretrainedConfig):
+    r"""
+    Based on LlavaConfig.
+
+    Args:
+        vision_config (`str`,  *optional*, timm model, defaults to `vit_so400m_patch14_siglip_384`):
+            The config object or dictionary of the vision backbone.
+        text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`):
+            The config object or dictionary of the text backbone.
+        ignore_index (`int`, *optional*, defaults to -100):
+            The ignore index for the loss function.
+        image_token_index (`int`, *optional*, defaults to 32000):
+            The image token index to encode the image prompt.
+        adapter_type (`str`, *optional*, defaults to `multiscale-pool`):
+            The adapter type.
+        adapter_config (`dict`, *optional*, defaults to `None`):
+"""
+
+    model_type = "centurio"
+    is_composition = True
+
+    def __init__(
+        self,
+        timm_model="vit_so400m_patch14_siglip_384",
+        image_hidden_size=1024,
+        text_config=None,
+        ignore_index=-100,
+        image_token_index=32000,
+        adapter_type="multiscale-pool",
+        adapter_config=None,
+        **kwargs,
+    ):
+        self.ignore_index = ignore_index
+        self.image_token_index = image_token_index
+        self.adapter_type = adapter_type
+        self.adapter_config = adapter_config
+
+        self.timm_model = timm_model
+        self.image_hidden_size = image_hidden_size
+
+        if isinstance(text_config, dict):
+            text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "llama"
+            text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
+        elif text_config is None:
+            text_config = CONFIG_MAPPING["llama"]()
+
+        self.text_config = text_config
+
+        super().__init__(**kwargs)
+
+
+# q = CenturioConfig(
+#     text_config=AutoConfig.from_pretrained("Qwen/Qwen2.5-7B-Instruct"),
+#     image_token_index=151665,
+#     adapter_type="multiscale-pool",
+#     adapter_config=dict(adapter_multi_scale=2),
+#     attn_implementation="flash_attention_2"
+# )
+# q.save_pretrained("centurio_qwen")
+#
+# a = CenturioConfig(
+#     text_config=AutoConfig.from_pretrained("CohereForAI/aya-expanse-8b"),
+#     image_token_index=255029,
+#     adapter_type="multiscale-pool",
+#     adapter_config=dict(adapter_multi_scale=2),
+#     attn_implementation="flash_attention_2"
+# )
+# a.save_pretrained("centurio_aya")

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143f1c4929f1487216361251bd0809789efb76db31735f647e66b787352153d3
+size 4936298336

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af78e75452fe0b798bc5eb8686a1fef5993187a818b800835a422e271a20653
+size 4915826008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c54b17e9987dcb9f7669e55160c753328df6aabeb2be741ab37907c1eafe53
+size 4999721000

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0543f5aad8d2294adb78fc8dfa3c4037e32aaa6335519855b0ea2be96f6a901
+size 2969639688

model.safetensors.index.json

@@ -0,0 +1,611 @@
+{
+  "metadata": {
+    "total_size": 17821413632
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "multi_modal_projector.adapter.linear_1.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.adapter.linear_1.weight": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.adapter.linear_2.bias": "model-00001-of-00004.safetensors",
+    "multi_modal_projector.adapter.linear_2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.kv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.kv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.latent": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.norm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.norm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.q.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.attn_pool.q.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.norm.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.norm.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
+    "vision_tower.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
+    "vision_tower.pos_embed": "model-00001-of-00004.safetensors"
+  }
+}