mv up_proj

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "_name_or_path": "zhuoyanxu/ada-llava-v1.5-13b",
   "architectures": [
     "AdaLlavaLlamaForCausalLM"
   ],
@@ -30,21 +30,23 @@
   "num_attention_heads": 40,
   "num_hidden_layers": 40,
   "num_key_value_heads": 40,
+  "num_prefix_layers": 20,
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "scheduler_type": "L",
   "tie_word_embeddings": false,
+  "token_selecting": "none",
   "tokenizer_model_max_length": 2048,
   "tokenizer_padding_side": "right",
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.37.2",
   "tune_mm_mlp_adapter": false,
   "tune_mm_vision_resampler": false,
   "unfreeze_mm_vision_tower": false,
   "use_cache": true,
   "use_mm_proj": true,
-  "vocab_size": 32000,
-  "num_prefix_layers": 20
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
   "max_length": 4096,
   "pad_token_id": 0,

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3d0a02060ec25ea1ce4d2bd38b683df958e358272884c33422aae2df0db034
-size 4978265800
+oid sha256:16249c9de0f3d63cdb2c62e89fcf9e33ba09f82be124a6073de994e782ea0520
+size 4978265728

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5bacd6f1b0fe64c9c661508fb2a567bcb25be53607e43379298ffa88f3cc6c
-size 4970422232
+oid sha256:8b0e31edfa6a1092d690374efb77ed027b67ebfffc0f034b7e26c4f6714bc2c9
+size 4970422160

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f04e9c5ee1bee8aea3402b1b7387825d41530e3889d4559ad01d63ad0a720d
-size 4970422256
+oid sha256:be7a18b493ecf5f67a22e952c401dcd5f0dc82a512382f79f44ad9f879403ab0
+size 4970422184

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adda2cfd92b028031ff258ec61900d05741627e90a8f2ea9d453e61894873675
-size 4933701504
+oid sha256:e85ca6a8611cb022dc7d32e5ce45bb359b6175f2ede5e482780768301b9a6148
+size 4933701432

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9687077783360889df62bbd9bfa70f32dc2e0534473fbddce5c9d99148bf6384
-size 4933722216
+oid sha256:a023e93c87f8d55574e92268e8297cd9448e9ffef07be5d3a0fd69b52237e2db
+size 4933722144

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d8cf23bf6bba32f545020a21794614a929d4d7918fff428b8f2e99f674f8a5
-size 1970526072
+oid sha256:fa39f59c2dfd2a9ee396265e0e873665875f3be0b3f8b60a0772596b5f95b1d4
+size 1363449808

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 26756955176
+    "total_size": 26149940264
   },
   "weight_map": {
     "lm_head.weight": "model-00006-of-00006.safetensors",
@@ -370,404 +370,13 @@
     "model.mm_projector.2.bias": "model-00006-of-00006.safetensors",
     "model.mm_projector.2.weight": "model-00006-of-00006.safetensors",
     "model.norm.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00006-of-00006.safetensors",
     "scheduler.mlp_head.bias": "model-00006-of-00006.safetensors",
     "scheduler.mlp_head.weight": "model-00006-of-00006.safetensors",
-    "scheduler_up_proj.net.0.bias": "model-00006-of-00006.safetensors",
-    "scheduler_up_proj.net.0.weight": "model-00006-of-00006.safetensors",
-    "scheduler_up_proj.net.1.bias": "model-00006-of-00006.safetensors",
-    "scheduler_up_proj.net.1.weight": "model-00006-of-00006.safetensors",
-    "scheduler_up_proj.net.3.bias": "model-00006-of-00006.safetensors",
-    "scheduler_up_proj.net.3.weight": "model-00006-of-00006.safetensors"
+    "scheduler.scheduler_up_proj.net.0.bias": "model-00006-of-00006.safetensors",
+    "scheduler.scheduler_up_proj.net.0.weight": "model-00006-of-00006.safetensors",
+    "scheduler.scheduler_up_proj.net.1.bias": "model-00006-of-00006.safetensors",
+    "scheduler.scheduler_up_proj.net.1.weight": "model-00006-of-00006.safetensors",
+    "scheduler.scheduler_up_proj.net.3.bias": "model-00006-of-00006.safetensors",
+    "scheduler.scheduler_up_proj.net.3.weight": "model-00006-of-00006.safetensors"
   }
 }

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,