Upload 6 files

added_tokens.json

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

config.json

@@ -0,0 +1,179 @@
+{
+  "architectures": [
+    "OmChatForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_grid_pinpoints": "[(896, 896), (448, 896), (896, 448), (448, 1344), (1344, 448), (1344, 896),(896, 1344), (1344, 1344)]",
+  "image_token_index": 32000,
+  "projector_hidden_act": "gelu",
+  "auto_map": {
+    "AutoConfig": "configuration_omchat.OmChatConfig",
+    "AutoModel": "modeling_omchat.OmChatForConditionalGeneration"
+  },
+  "text_config": {
+    "_name_or_path": "../resources/Qwen2-7B",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "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": 151643,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": 131072,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "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_sliding_window": false,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 3200,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 448,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 12800,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "intern_vit_6b",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 25,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 45,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qk_normalization": true,
+    "qkv_bias": false,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "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": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_flash_attn": true
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "default"
+}

flash_attention.py

@@ -0,0 +1,76 @@
+import torch
+import torch.nn as nn
+from einops import rearrange
+
+try:  # v1
+    from flash_attn.flash_attn_interface import \
+        flash_attn_unpadded_qkvpacked_func
+except:  # v2
+    from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
+
+from flash_attn.bert_padding import pad_input, unpad_input
+
+
+class FlashAttention(nn.Module):
+    """Implement the scaled dot product attention with softmax.
+    Arguments
+    ---------
+        softmax_scale: The temperature to use for the softmax attention.
+                      (default: 1/sqrt(d_keys) where d_keys is computed at
+                      runtime)
+        attention_dropout: The dropout rate to apply to the attention
+                           (default: 0.0)
+    """
+
+    def __init__(self, softmax_scale=None, attention_dropout=0.0, device=None, dtype=None):
+        super().__init__()
+        self.softmax_scale = softmax_scale
+        self.dropout_p = attention_dropout
+
+    def forward(self, qkv, key_padding_mask=None, causal=False, cu_seqlens=None,
+                max_s=None, need_weights=False):
+        """Implements the multihead softmax attention.
+        Arguments
+        ---------
+            qkv: The tensor containing the query, key, and value. (B, S, 3, H, D) if key_padding_mask is None
+                if unpadded: (nnz, 3, h, d)
+            key_padding_mask: a bool tensor of shape (B, S)
+        """
+        assert not need_weights
+        assert qkv.dtype in [torch.float16, torch.bfloat16]
+        assert qkv.is_cuda
+
+        if cu_seqlens is None:
+            batch_size = qkv.shape[0]
+            seqlen = qkv.shape[1]
+            if key_padding_mask is None:
+                qkv = rearrange(qkv, 'b s ... -> (b s) ...')
+                max_s = seqlen
+                cu_seqlens = torch.arange(0, (batch_size + 1) * seqlen, step=seqlen, dtype=torch.int32,
+                                          device=qkv.device)
+                output = flash_attn_unpadded_qkvpacked_func(
+                    qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                    softmax_scale=self.softmax_scale, causal=causal
+                )
+                output = rearrange(output, '(b s) ... -> b s ...', b=batch_size)
+            else:
+                nheads = qkv.shape[-2]
+                x = rearrange(qkv, 'b s three h d -> b s (three h d)')
+                x_unpad, indices, cu_seqlens, max_s = unpad_input(x, key_padding_mask)
+                x_unpad = rearrange(x_unpad, 'nnz (three h d) -> nnz three h d', three=3, h=nheads)
+                output_unpad = flash_attn_unpadded_qkvpacked_func(
+                    x_unpad, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                    softmax_scale=self.softmax_scale, causal=causal
+                )
+                output = rearrange(pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'),
+                                             indices, batch_size, seqlen),
+                                   'b s (h d) -> b s h d', h=nheads)
+        else:
+            assert max_s is not None
+            output = flash_attn_unpadded_qkvpacked_func(
+                qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
+                softmax_scale=self.softmax_scale, causal=causal
+            )
+
+        return output, None
+

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52883a7cb1e9f433d51b03b3273da51a4eb4bcff21f6ed5b55cdfcad03724aa
+size 4988569176

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6903ac7dc555112d0eb467315065d4513068da8091ce3c7e9bc04cf5f6c071
+size 4991497656

model.safetensors.index.json

@@ -0,0 +1,939 @@
+{
+  "metadata": {
+    "total_size": 26352867072
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.norm.weight": "model-00006-of-00006.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00003-of-00006.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00003-of-00006.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00003-of-00006.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.embeddings.class_embedding": "model-00001-of-00006.safetensors",
+    "vision_tower.embeddings.patch_embedding.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.embeddings.patch_embedding.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.embeddings.position_embedding": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.0.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.1.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.10.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.11.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.12.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.13.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.14.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.15.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.16.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.17.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.18.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.19.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.2.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.20.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.21.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.22.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.23.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.24.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.25.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.26.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.27.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.28.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.29.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.3.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.30.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.31.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.32.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.33.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.34.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.35.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.36.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.37.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.38.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.mlp.fc1.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.mlp.fc1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.mlp.fc2.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.mlp.fc2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.norm1.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.39.norm2.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.4.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.attn.proj.bias": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.attn.proj.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.attn.qkv.weight": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.ls1": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.ls2": "model-00002-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.mlp.fc1.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.mlp.fc1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.mlp.fc2.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.mlp.fc2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.norm1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.40.norm2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.attn.proj.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.attn.proj.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.attn.qkv.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.ls1": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.ls2": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.mlp.fc1.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.mlp.fc1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.mlp.fc2.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.mlp.fc2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.norm1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.41.norm2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.attn.proj.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.attn.proj.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.attn.qkv.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.ls1": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.ls2": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.mlp.fc1.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.mlp.fc1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.mlp.fc2.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.mlp.fc2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.norm1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.42.norm2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.attn.proj.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.attn.proj.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.attn.qkv.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.ls1": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.ls2": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.mlp.fc1.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.mlp.fc1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.mlp.fc2.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.mlp.fc2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.norm1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.43.norm2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.attn.proj.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.attn.proj.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.attn.qkv.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.ls1": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.ls2": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.mlp.fc1.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.mlp.fc1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.mlp.fc2.bias": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.mlp.fc2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.norm1.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.44.norm2.weight": "model-00003-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.5.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.6.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.7.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.8.norm2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.attn.proj.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.attn.proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.attn.qkv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.ls1": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.ls2": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.norm1.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.encoder.layers.9.norm2.weight": "model-00001-of-00006.safetensors"
+  }
+}