Training in progress, step 150

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "llava-hf/llava-v1.6-mistral-7b-hf",
+  "base_model_name_or_path": "llava-hf/llava-1.5-13b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "up_proj",
     "k_proj",
-    "gate_proj",
     "down_proj",
-    "up_proj",
-    "o_proj"
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff09724160dcf4cf64f0f6eb34e5721245c37d345a0397afa63ea29ef656359
-size 8463296
+oid sha256:60deacf62330bdba260c97a08ef601aac7ef513c5904b0224b86fb9668676ac5
+size 9987008

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<<SYS>>\n' + message['content'][0]['text'] + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'user' %}{{ '[INST] ' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{{' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'][0]['text'] + '<\\s> '}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+}

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "llava-hf/llava-1.5-13b-hf",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "pad_token_id": 32001,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "meta-llama/Llama-2-13b-hf",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "hidden_size": 5120,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 40,
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "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",
+  "vocab_size": 32064
+}

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": "4.46.0"
+}

lorra_config.json

@@ -0,0 +1,8 @@
+{
+  "target_layers": "16",
+  "transform_layers": "14,15,16",
+  "lorra_alpha": 5.0,
+  "trainsets": null,
+  "valsets": null,
+  "full_layers": false
+}

preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "image_token": "<image>",
+  "patch_size": 14,
+  "processor_class": "LlavaNextProcessor",
+  "vision_feature_select_strategy": "default"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f818cd63c7316ae1e62afbadd188e62a718223fb17346dc11f2ca3d11ec3a1
+size 4962195433

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7595029c007700e701248e5542cdbbcbb5d03dadfffdc7e565b03b8de85f8481
+size 4970440162

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c704aaf16278a62555fa194046e2abab480760e51a7b35781170f8416baa7a2b
+size 4881290034

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed5b4920e3c41324c18d7b8f443133587f942eef1913cf61087490956059dca
+size 4933740356

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff4a93964e7cb18c57527bf1bfeb786d80bfe0ee3acbd9e7d2f1068850422bb
+size 4933740404

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764b406c3191284742a8c9a204a14a27eb2008ce6cef32d71f3b306b5d03ce94
+size 1693525384

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef30c1e1991eb8040eed3f9098aea8b1c5cfd9c88d93748a0d742340a0edbbb0
+size 7540

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3dff4f52e3fc33ed4747ea83922ab57838e6348cd1a1bc6e2c7dbbd6f61a89
+size 7412

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6ffa5bbe96266bada091e2c2c454c67c31bc275910066a2840b33ef31362c2
+size 328349270

pytorch_model.bin.index.json

@@ -0,0 +1,972 @@
+{
+  "metadata": {
+    "total_size": 41294395392
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "language_model.model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.42.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.43.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "language_model.model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.49.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.50.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.50.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.51.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.52.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "language_model.model.layers.53.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.53.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.54.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.55.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.56.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.57.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.58.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.59.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "language_model.model.layers.60.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.60.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.60.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.60.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.60.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.60.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.60.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.60.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.60.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "language_model.model.layers.61.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.61.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.62.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "language_model.model.norm.weight": "pytorch_model-00009-of-00009.bin",
+    "multi_modal_projector.linear_1.bias": "pytorch_model-00001-of-00009.bin",
+    "multi_modal_projector.linear_1.weight": "pytorch_model-00001-of-00009.bin",
+    "multi_modal_projector.linear_2.bias": "pytorch_model-00001-of-00009.bin",
+    "multi_modal_projector.linear_2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00009.bin",
+    "vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00009.bin"
+  }
+}

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -44,26 +44,21 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {
     "image_token": "<image>"
   },
   "image_token": "<image>",
-  "legacy": true,
-  "max_length": null,
+  "legacy": false,
   "model_max_length": 8192,
-  "pad_to_multiple_of": null,
   "pad_token": "</s>",
-  "pad_token_type_id": 0,
   "padding_side": "left",
-  "processor_class": "LlavaNextProcessor",
+  "processor_class": "LlavaProcessor",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b687191320ebcf3b23eba17022227dbbdb99144f49afde09c51ab32e4eacc1f2
+oid sha256:c90cb0dd2653fb282193c483f24890ea1bc5d9301aed963bb86c57bd02fa6829
 size 6840