update

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 64000,
+  "<pad>": 64001
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 64000,
+  "model_type": "llava",
+  "pad_token_id": 32000,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "hidden_size": 7168,
+    "intermediate_size": 20480,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 56,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 5000000.0,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 64064
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "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"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32001,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953359242ec0aa467fa3a9f388f795cc1b07a375ba0777d0d9acbd6fc11e9e1d
+size 4990104296

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f4b4a866bcc446376ff61f825e771c15b7128d26e1457295c2f8d9bd937069
+size 4991341824

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34340f966e770971b28c731be24b322433ff5a5582423f1ac8a6db180910784
+size 4756460288

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4193d1d2a172ea65195707132b07e888b6a28bb4f9734714368eb24b2b42539
+size 4991370808

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:952413494a5d843823a729b98ef1cec3708c3d3f9697a13c543b890ea1581d5b
+size 4756460312

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb5d0412618f78d2ac82eb0d7cb256a6bb3bf2bbfca1633db98ec068d7d99ae
+size 4756460312

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1bdd3474e853caf7d5e9ef60f8085858e9b75f0c9c4931f4ae139c1d3375de
+size 4991370808

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca6025ebcdcdd59cf6ef422fa711fbe7cce307ac26ebf56c4d8488de2e47896
+size 4756460312

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fb1e8ee2c46bbec1211303537882114bb314f510da1df7f3c090443ca40353
+size 4756460312

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689c55dafe1acccaf4a33fed16f09c638e428aeca67e69e45217d428b3934b6f
+size 4991370808

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c620a907d79c6e6e155969990534cea95edc37f92d6f445eedceb9a0a91d49c
+size 4756460312

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2e3d741151564275f6c66d90e4a19c847afd3c1340f3ff70ed97d09cfe372c
+size 4756460312

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f894caa7c095f3a549ae186a3573bdb9c18944f57cdcc75afcf41ed173f9f8
+size 4991370808

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02f1d8160a53ba2f51c2dd6966dfdc04e1ad51b145f33a40149f617c7e5f1f5
+size 4756460312

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823da70296b89d6934547b30d0120e4d8e122f29bcff411e6361078ea6e0896f
+size 1505667840

model.safetensors.index.json

@@ -0,0 +1,945 @@
+{
+  "metadata": {
+    "total_size": 69504153600
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.42.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "language_model.model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.46.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "language_model.model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.50.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.50.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.50.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "language_model.model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.51.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.55.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "language_model.model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.59.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "language_model.model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "language_model.model.norm.weight": "model-00015-of-00015.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00015.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00015.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00015.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00015.safetensors",
+    "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00015.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 4096,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}