Upload Ovis2ForConditionalGeneration

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe45868f9e8340da3df20dfc41839ac5ce1b4301ce6c49b9ff189853e7b3512e
-size 4999702488
+oid sha256:bfc7f6b32d60b91e83cbefe96970855d0b7371297fd118c162a3a3bcb0736eb5
+size 4999702392

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d19f486b1d9abade4f715a3a67a392577b565d97b1d3d1e0fc02c4428082ec
-size 804576872
+oid sha256:c84e4fdf6e06ad30bb3a4a64186a30ef0b6b6938782b29a0288b30c3752d4cd1
+size 804576880

model.safetensors.index.json

@@ -349,223 +349,223 @@
     "model.vision_tower.transformer.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.transformer.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.transformer.embeddings.rms_norm.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.vision_tower.transformer.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.0.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.1.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.10.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.11.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.12.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.13.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.14.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.15.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.16.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.17.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.18.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.19.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.2.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.20.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.21.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.22.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.23.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.3.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.4.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.5.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.6.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.7.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.8.rms_norm2.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.ffn.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.rms_norm1.weight": "model-00001-of-00002.safetensors",
+    "model.vision_tower.transformer.encoder.layers.9.rms_norm2.weight": "model-00001-of-00002.safetensors",
     "model.vision_tower.transformer.rms_norm.weight": "model-00001-of-00002.safetensors",
-    "model.visual_table.weight": "model-00002-of-00002.safetensors"
+    "model.visual_embeddings_table.weight": "model-00002-of-00002.safetensors"
   }
 }