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 +1,1367 @@
+{
+  "metadata": {
+    "total_size": 6865049152
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.audio_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.audio_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.audio_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.embed_positions.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.embed_tokens.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.conv1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.conv1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.conv2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.conv2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.embed_positions.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.audio_tower.audio_tower.encoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors"
+  }
+}