diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
new file mode 100644--- /dev/null
+++ "b/model.safetensors.index.json"
@@ -0,0 +1,1011 @@
+{
+  "metadata": {
+    "total_size": 15983659652
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.models.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.models.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.models.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.models.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_0.attention_layer.linear_1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_0.attention_layer.linear_2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_0.attention_layer.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_0.attention_layer.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_1.attention_layer.linear_1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_1.attention_layer.linear_2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_1.attention_layer.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_1.attention_layer.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_2.attention_layer.linear_1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_2.attention_layer.linear_2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_2.attention_layer.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_2.attention_layer.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_3.attention_layer.linear_1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_3.attention_layer.linear_2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_3.attention_layer.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.aggregate_3.attention_layer.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.norm_context.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.norm_context.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.norm_quy.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.norm_quy.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.proj_context.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.proj_out.linear_1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.proj_out.linear_2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.weight_mlp.linear_1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.VTMerge.layers.0.weight_mlp.linear_2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.clip_vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.bn1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.bn1.num_batches_tracked": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.bn1.running_mean": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.bn1.running_var": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.bn1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.deconv1.1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv1.1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv1.1.num_batches_tracked": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv1.1.running_mean": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv1.1.running_var": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv2.0.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv2.1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv2.1.num_batches_tracked": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv2.1.running_mean": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv2.1.running_var": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.conv2.1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.fu.bn.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.fu.bn.num_batches_tracked": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.fu.bn.running_mean": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.fu.bn.running_var": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.fu.bn.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.ffc.fu.conv_layer.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn1.num_batches_tracked": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn1.running_mean": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn1.running_var": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn2.num_batches_tracked": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn2.running_mean": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn2.running_var": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_bn2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_conv1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_trans.fc_out.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_trans.fc_out.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_trans.keys.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_trans.queries.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.bjhead.merge_trans.values.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.downsample.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.downsample.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.0.downsample.reduction.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.downsample.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.downsample.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.1.downsample.reduction.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.2.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.3.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.4.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.blocks.5.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.downsample.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.downsample.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.2.downsample.reduction.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.attn.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.attn.qkv.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.attn.relative_position_bias_table": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.attn.relative_position_index": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.layers.3.blocks.1.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.norm3.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.norm3.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.patch_embed.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.patch_embed.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.patch_embed.proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.body.patch_embed.proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_inner2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_inner2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_inner3.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_inner3.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_inner4.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_inner4.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_layer2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_layer2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_layer3.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_layer3.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_layer4.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.fpn_layer4.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.top_blocks.p6.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.top_blocks.p6.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.top_blocks.p7.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.glip_vision_tower.glip_model.fpn.top_blocks.p7.weight": "model-00003-of-00004.safetensors"
+  }
+}