Upload zamba2_vl_2.7b

pytorch_model-00001-of-00002.bin → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5bc82d0f59371c478f457dc780de7f73d85a786bab9e1bc20f32e00942b9766
-size 4991953458
+oid sha256:a640b20bae6c7d467b827b63d1a556fac44182c7e914306f74772a79bffc2750
+size 4991769648

pytorch_model-00002-of-00002.bin → model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3e5fe7179b23b11a892b925c5e78916ad63fc337de993867e1df1160f54c07
-size 1674246401
+oid sha256:6402dd39c1f23aa424377090c8e14a7ab694cfeb771541ca8a5ba8ef8ca9a134
+size 1674206208

model.safetensors.index.json

@@ -0,0 +1,928 @@
+{
+  "metadata": {
+    "total_size": 6665864000
+  },
+  "weight_map": {
+    "vision_tower.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.linear.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.linear.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.0.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.1.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.linear.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.linear.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.linear.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.30.mamba_decoder.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.A_log": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.D": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.33.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.linear.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.36.mamba_decoder.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.linear.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.42.mamba_decoder.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.linear.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.47.mamba_decoder.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.48.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.linear.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.51.mamba_decoder.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.A_log": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.D": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.final_layernorm.weight": "model-00002-of-00002.safetensors"
+  }
+}