(Trained with Unsloth)

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 3075098624,
-    "total_size": 6150197248
+    "total_parameters": 4022468096,
+    "total_size": 8044936192
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -10,8 +10,10 @@
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -19,8 +21,10 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -28,8 +32,10 @@
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -37,8 +43,10 @@
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -46,8 +54,10 @@
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -55,8 +65,10 @@
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -64,8 +76,10 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -73,8 +87,10 @@
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -82,8 +98,10 @@
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -91,8 +109,10 @@
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -100,8 +120,10 @@
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -109,8 +131,10 @@
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -118,98 +142,120 @@
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -217,8 +263,10 @@
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -226,8 +274,10 @@
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -235,8 +285,10 @@
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -244,8 +296,10 @@
     "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -253,8 +307,10 @@
     "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -262,8 +318,10 @@
     "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -271,8 +329,10 @@
     "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -280,8 +340,10 @@
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -289,8 +351,10 @@
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -298,8 +362,10 @@
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -307,8 +373,10 @@
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -316,8 +384,10 @@
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -325,8 +395,10 @@
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"