Upload folder using huggingface_hub

config.json

@@ -0,0 +1,90 @@
+{
+  "_name_or_path": "tiiuae/falcon-11B-vlm",
+  "architectures": [
+    "FalconVlmForConditionalGeneration"
+  ],
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_token_index": 65024,
+  "model_type": "llava_next",
+  "pad_token_id": 0,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "tiiuae/falcon-11B-vlm",
+    "architectures": [
+      "FalconForCausalLM"
+    ],
+    "auto_map": {
+      "AutoConfig": "configuration_falcon.FalconConfig",
+      "AutoModel": "modeling_falcon.FalconModel",
+      "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
+      "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
+      "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
+      "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
+    },
+    "bias": false,
+    "bos_token_id": 11,
+    "eos_token_id": 11,
+    "ff_factor": 4,
+    "ffn_hidden_size": 16384,
+    "hidden_dropout": 0.0,
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "max_position_embeddings": 8192,
+    "model_type": "falcon",
+    "multi_query": true,
+    "new_decoder_architecture": true,
+    "num_attention_heads": 32,
+    "num_hidden_layers": 60,
+    "num_kv_heads": 8,
+    "num_ln_in_parallel_attn": 1,
+    "parallel_attn": true,
+    "rope_scaling": null,
+    "rope_theta": 500042.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.2",
+    "use_cache": true,
+    "vocab_size": 65024
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0.dev0",
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 65024
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49612d0ea741f91a0b5266eea0a08596901ab8f5651e6a4e8ed255698ef1fbb8
+size 4978853960

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37921da5d0f87649b8aa73ead0bf928a929d39e2efdbd23ad823e7be8011c2b
+size 4932742248

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937c78f91431d2540d232c8ec05a9e3b2043c37691c70e40b00ad4b1eee4ba58
+size 4932742248

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e5440dc3060b108a2ef71299c7531d33387eb38040d8fec7a0aee83f1259c4
+size 4932742248

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3364d4a029a59e749207c151cca44a4226faad0f27fc10d1c67dd6831763cbf9
+size 3077650256

model.safetensors.index.json

@@ -0,0 +1,767 @@
+{
+  "metadata": {
+    "total_size": 22854627328
+  },
+  "weight_map": {
+    "image_newline": "model-00001-of-00005.safetensors",
+    "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.0.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.1.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.10.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.11.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.12.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.12.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.13.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.13.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.14.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.14.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.15.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.15.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.16.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.16.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.17.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.17.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.18.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.18.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.19.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.19.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.2.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.20.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.20.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.21.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.21.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.22.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.22.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.22.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.23.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.23.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.23.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.24.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.24.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.24.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.25.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.25.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.25.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.26.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.26.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "language_model.transformer.h.27.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.27.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.28.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.28.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.29.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.29.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.3.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.30.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.30.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.31.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.31.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.31.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.32.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.32.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.32.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.32.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.32.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.33.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.33.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.33.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.33.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.33.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.33.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.34.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.34.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.34.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.34.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.34.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.34.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.35.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.35.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.35.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.35.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.35.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.35.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.36.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.36.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.36.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.36.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.36.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.36.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.37.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.37.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.37.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.37.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.37.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.37.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.38.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.38.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.38.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.38.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.38.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.38.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.39.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.39.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.39.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.39.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.39.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.39.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.4.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.40.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.40.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.40.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.40.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.40.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "language_model.transformer.h.41.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.41.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.41.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.41.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.41.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.42.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.42.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.42.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.42.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.42.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.43.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.43.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.43.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.43.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.43.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.44.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.44.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.44.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.44.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.44.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.44.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.45.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.45.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.45.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.45.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.45.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.45.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.46.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.46.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.46.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.46.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.46.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.46.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.47.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.47.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.47.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.47.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.47.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.47.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.48.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.48.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.48.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.48.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.48.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.48.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.49.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.49.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.49.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.49.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.49.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.49.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.5.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.50.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.50.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.50.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.50.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.50.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.50.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.51.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.51.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.51.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.51.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.51.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.51.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.52.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.52.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.52.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.52.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.52.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.52.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.53.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.53.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.53.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.53.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.53.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.53.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.54.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.54.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.54.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.54.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.54.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.54.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "language_model.transformer.h.55.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.55.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.55.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.55.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.55.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.55.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.56.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.56.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.56.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.56.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.56.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.56.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.57.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.57.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.57.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.57.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.57.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.57.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.58.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.58.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.58.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.58.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.58.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.58.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.59.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.59.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.59.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.59.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.59.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.59.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.h.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.6.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.7.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.8.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.9.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "language_model.transformer.ln_f.bias": "model-00005-of-00005.safetensors",
+    "language_model.transformer.ln_f.weight": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00005-of-00005.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.transformer.word_embeddings.weight": "model-00001-of-00005.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": ">>TITLE<<",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65024": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": ">>TITLE<<",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}