Update model.safetensors.index.json

model.safetensors.index.json

@@ -10,10 +10,10 @@
     "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -24,10 +24,10 @@
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -38,10 +38,10 @@
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -52,10 +52,10 @@
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -66,10 +66,10 @@
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -80,10 +80,10 @@
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -94,10 +94,10 @@
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -108,10 +108,10 @@
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -122,10 +122,10 @@
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -136,10 +136,10 @@
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -150,10 +150,10 @@
     "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -164,10 +164,10 @@
     "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -178,10 +178,10 @@
     "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -192,10 +192,10 @@
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -206,10 +206,10 @@
     "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -220,10 +220,10 @@
     "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -234,10 +234,10 @@
     "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -248,10 +248,10 @@
     "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -262,10 +262,10 @@
     "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -276,10 +276,10 @@
     "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -290,10 +290,10 @@
     "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -304,10 +304,10 @@
     "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -318,10 +318,10 @@
     "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -332,10 +332,10 @@
     "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -346,10 +346,10 @@
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.block_sparse_moe.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.block_sparse_moe.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.block_sparse_moe.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.block_sparse_moe.mlp.fc2.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
@@ -360,10 +360,10 @@
     "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.block_sparse_moe.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.block_sparse_moe.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.block_sparse_moe.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.block_sparse_moe.mlp.fc2.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
@@ -374,10 +374,10 @@
     "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -388,10 +388,10 @@
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -402,10 +402,10 @@
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -416,10 +416,10 @@
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -430,10 +430,10 @@
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
@@ -444,10 +444,10 @@
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",