Upload mlx/model.safetensors.index.json with huggingface_hub

mlx/model.safetensors.index.json

@@ -1,7 +1,6 @@
 {
     "metadata": {
-        "total_size": 1736187904,
-        "total_parameters": 3085938688
+        "total_size": 2262920192
     },
     "weight_map": {
         "model.embed_tokens.biases": "model.safetensors",
@@ -18,18 +17,17 @@
         "model.layers.0.mlp.up_proj.scales": "model.safetensors",
         "model.layers.0.mlp.up_proj.weight": "model.safetensors",
         "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
@@ -44,18 +42,17 @@
         "model.layers.1.mlp.up_proj.scales": "model.safetensors",
         "model.layers.1.mlp.up_proj.weight": "model.safetensors",
         "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
@@ -70,18 +67,17 @@
         "model.layers.10.mlp.up_proj.scales": "model.safetensors",
         "model.layers.10.mlp.up_proj.weight": "model.safetensors",
         "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
@@ -96,18 +92,17 @@
         "model.layers.11.mlp.up_proj.scales": "model.safetensors",
         "model.layers.11.mlp.up_proj.weight": "model.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
@@ -122,18 +117,17 @@
         "model.layers.12.mlp.up_proj.scales": "model.safetensors",
         "model.layers.12.mlp.up_proj.weight": "model.safetensors",
         "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
@@ -148,18 +142,17 @@
         "model.layers.13.mlp.up_proj.scales": "model.safetensors",
         "model.layers.13.mlp.up_proj.weight": "model.safetensors",
         "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
@@ -174,18 +167,17 @@
         "model.layers.14.mlp.up_proj.scales": "model.safetensors",
         "model.layers.14.mlp.up_proj.weight": "model.safetensors",
         "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
@@ -200,18 +192,17 @@
         "model.layers.15.mlp.up_proj.scales": "model.safetensors",
         "model.layers.15.mlp.up_proj.weight": "model.safetensors",
         "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
@@ -226,18 +217,17 @@
         "model.layers.16.mlp.up_proj.scales": "model.safetensors",
         "model.layers.16.mlp.up_proj.weight": "model.safetensors",
         "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
@@ -252,18 +242,17 @@
         "model.layers.17.mlp.up_proj.scales": "model.safetensors",
         "model.layers.17.mlp.up_proj.weight": "model.safetensors",
         "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
@@ -278,18 +267,17 @@
         "model.layers.18.mlp.up_proj.scales": "model.safetensors",
         "model.layers.18.mlp.up_proj.weight": "model.safetensors",
         "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
@@ -304,18 +292,17 @@
         "model.layers.19.mlp.up_proj.scales": "model.safetensors",
         "model.layers.19.mlp.up_proj.weight": "model.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
@@ -330,18 +317,17 @@
         "model.layers.2.mlp.up_proj.scales": "model.safetensors",
         "model.layers.2.mlp.up_proj.weight": "model.safetensors",
         "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
@@ -356,18 +342,17 @@
         "model.layers.20.mlp.up_proj.scales": "model.safetensors",
         "model.layers.20.mlp.up_proj.weight": "model.safetensors",
         "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
@@ -382,18 +367,17 @@
         "model.layers.21.mlp.up_proj.scales": "model.safetensors",
         "model.layers.21.mlp.up_proj.weight": "model.safetensors",
         "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
@@ -408,18 +392,17 @@
         "model.layers.22.mlp.up_proj.scales": "model.safetensors",
         "model.layers.22.mlp.up_proj.weight": "model.safetensors",
         "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
@@ -434,18 +417,17 @@
         "model.layers.23.mlp.up_proj.scales": "model.safetensors",
         "model.layers.23.mlp.up_proj.weight": "model.safetensors",
         "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
@@ -460,18 +442,17 @@
         "model.layers.24.mlp.up_proj.scales": "model.safetensors",
         "model.layers.24.mlp.up_proj.weight": "model.safetensors",
         "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.24.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.24.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.24.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
@@ -486,18 +467,17 @@
         "model.layers.25.mlp.up_proj.scales": "model.safetensors",
         "model.layers.25.mlp.up_proj.weight": "model.safetensors",
         "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.25.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.25.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.25.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
@@ -512,18 +492,17 @@
         "model.layers.26.mlp.up_proj.scales": "model.safetensors",
         "model.layers.26.mlp.up_proj.weight": "model.safetensors",
         "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.26.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.26.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.26.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
@@ -538,18 +517,17 @@
         "model.layers.27.mlp.up_proj.scales": "model.safetensors",
         "model.layers.27.mlp.up_proj.weight": "model.safetensors",
         "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.27.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.27.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.27.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
@@ -564,18 +542,17 @@
         "model.layers.28.mlp.up_proj.scales": "model.safetensors",
         "model.layers.28.mlp.up_proj.weight": "model.safetensors",
         "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.28.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.28.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.28.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
@@ -590,18 +567,17 @@
         "model.layers.29.mlp.up_proj.scales": "model.safetensors",
         "model.layers.29.mlp.up_proj.weight": "model.safetensors",
         "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.29.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.29.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.29.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
@@ -616,18 +592,17 @@
         "model.layers.3.mlp.up_proj.scales": "model.safetensors",
         "model.layers.3.mlp.up_proj.weight": "model.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
@@ -642,18 +617,17 @@
         "model.layers.30.mlp.up_proj.scales": "model.safetensors",
         "model.layers.30.mlp.up_proj.weight": "model.safetensors",
         "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.30.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.30.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.30.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
@@ -668,18 +642,17 @@
         "model.layers.31.mlp.up_proj.scales": "model.safetensors",
         "model.layers.31.mlp.up_proj.weight": "model.safetensors",
         "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.31.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.31.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.31.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
@@ -694,18 +667,17 @@
         "model.layers.32.mlp.up_proj.scales": "model.safetensors",
         "model.layers.32.mlp.up_proj.weight": "model.safetensors",
         "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.32.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.32.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.32.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.32.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.32.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
@@ -720,18 +692,17 @@
         "model.layers.33.mlp.up_proj.scales": "model.safetensors",
         "model.layers.33.mlp.up_proj.weight": "model.safetensors",
         "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.33.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.33.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.33.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.33.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.33.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
@@ -746,18 +717,17 @@
         "model.layers.34.mlp.up_proj.scales": "model.safetensors",
         "model.layers.34.mlp.up_proj.weight": "model.safetensors",
         "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.34.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.34.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.34.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.34.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.34.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
@@ -772,18 +742,17 @@
         "model.layers.35.mlp.up_proj.scales": "model.safetensors",
         "model.layers.35.mlp.up_proj.weight": "model.safetensors",
         "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.35.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.35.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.35.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.35.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.35.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
@@ -798,18 +767,17 @@
         "model.layers.4.mlp.up_proj.scales": "model.safetensors",
         "model.layers.4.mlp.up_proj.weight": "model.safetensors",
         "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
@@ -824,18 +792,17 @@
         "model.layers.5.mlp.up_proj.scales": "model.safetensors",
         "model.layers.5.mlp.up_proj.weight": "model.safetensors",
         "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
@@ -850,18 +817,17 @@
         "model.layers.6.mlp.up_proj.scales": "model.safetensors",
         "model.layers.6.mlp.up_proj.weight": "model.safetensors",
         "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
@@ -876,18 +842,17 @@
         "model.layers.7.mlp.up_proj.scales": "model.safetensors",
         "model.layers.7.mlp.up_proj.weight": "model.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
@@ -902,18 +867,17 @@
         "model.layers.8.mlp.up_proj.scales": "model.safetensors",
         "model.layers.8.mlp.up_proj.weight": "model.safetensors",
         "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
@@ -928,18 +892,17 @@
         "model.layers.9.mlp.up_proj.scales": "model.safetensors",
         "model.layers.9.mlp.up_proj.weight": "model.safetensors",
         "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
-        "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
         "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
         "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
         "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
         "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
         "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
         "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
         "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
         "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.v_proj.weight": "model.safetensors",