diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,6 +1,7 @@
 {
     "metadata": {
-        "total_size": 15576115200
+        "total_size": 15693948928,
+        "total_parameters": 14770033664
     },
     "weight_map": {
         "lm_head.biases": "model-00003-of-00003.safetensors",
@@ -20,15 +21,18 @@
         "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -43,15 +47,18 @@
         "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -66,15 +73,18 @@
         "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -89,15 +99,18 @@
         "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -112,87 +125,99 @@
         "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
         "model.layers.15.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.15.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
         "model.layers.16.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
@@ -204,15 +229,18 @@
         "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -227,15 +255,18 @@
         "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -250,15 +281,18 @@
         "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -273,15 +307,18 @@
         "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -296,15 +333,18 @@
         "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -319,15 +359,18 @@
         "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -342,15 +385,18 @@
         "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -365,15 +411,18 @@
         "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -388,15 +437,18 @@
         "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -411,15 +463,18 @@
         "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -434,15 +489,18 @@
         "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -457,15 +515,18 @@
         "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
@@ -480,64 +541,73 @@
         "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
         "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
@@ -549,110 +619,125 @@
         "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.33.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.33.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
         "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
         "model.layers.34.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
@@ -664,15 +749,18 @@
         "model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
@@ -687,15 +775,18 @@
         "model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
@@ -710,15 +801,18 @@
         "model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
@@ -733,15 +827,18 @@
         "model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
@@ -756,15 +853,18 @@
         "model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
@@ -779,15 +879,18 @@
         "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
         "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
@@ -802,18 +905,229 @@
         "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
         "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
         "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
@@ -825,15 +1139,18 @@
         "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -848,15 +1165,18 @@
         "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -871,15 +1191,18 @@
         "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -894,15 +1217,18 @@
         "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
@@ -917,15 +1243,18 @@
         "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",