diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,11 +1,13 @@
 {
     "metadata": {
-        "total_size": 41198698496
+        "total_size": 39688355840
     },
     "weight_map": {
         "lm_head.biases": "model-00008-of-00008.safetensors",
         "lm_head.scales": "model-00008-of-00008.safetensors",
         "lm_head.weight": "model-00008-of-00008.safetensors",
+        "model.embed_tokens.biases": "model-00001-of-00008.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00008.safetensors",
         "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
         "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
         "model.layers.0.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
@@ -214,17 +216,17 @@
         "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
         "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
         "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors",
         "model.layers.17.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
         "model.layers.17.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
         "model.layers.17.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
         "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
         "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
         "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.17.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.17.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
         "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
         "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
         "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
@@ -237,52 +239,52 @@
         "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
         "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
         "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
         "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
         "model.layers.2.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.2.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
@@ -307,28 +309,28 @@
         "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
         "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors",
-        "model.layers.20.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.20.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.20.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.20.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
         "model.layers.20.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.20.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
         "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
         "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
-        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
         "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors",
         "model.layers.21.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.21.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
@@ -490,17 +492,17 @@
         "model.layers.27.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
         "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003-of-00008.safetensors",
         "model.layers.28.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.28.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
         "model.layers.28.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
         "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
         "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.28.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.28.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
         "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
         "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
@@ -513,29 +515,29 @@
         "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
         "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
         "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
         "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
         "model.layers.3.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.3.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
@@ -559,52 +561,52 @@
         "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
         "model.layers.31.input_layernorm.weight": "model-00004-of-00008.safetensors",
-        "model.layers.31.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.31.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.31.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.31.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
         "model.layers.31.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
         "model.layers.31.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
         "model.layers.31.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
         "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
         "model.layers.32.input_layernorm.weight": "model-00004-of-00008.safetensors",
         "model.layers.32.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
         "model.layers.32.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
@@ -766,17 +768,17 @@
         "model.layers.38.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
         "model.layers.38.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
         "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.39.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00004-of-00008.safetensors",
         "model.layers.39.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
         "model.layers.39.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
         "model.layers.39.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
         "model.layers.39.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
         "model.layers.39.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
         "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
-        "model.layers.39.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.39.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
         "model.layers.39.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
         "model.layers.39.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
         "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
@@ -812,75 +814,75 @@
         "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-        "model.layers.40.input_layernorm.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.input_layernorm.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
         "model.layers.42.input_layernorm.weight": "model-00005-of-00008.safetensors",
-        "model.layers.42.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.42.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.42.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.42.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.42.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.42.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.42.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.42.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.42.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
         "model.layers.42.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
         "model.layers.42.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
         "model.layers.42.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
         "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
-        "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.42.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
         "model.layers.43.input_layernorm.weight": "model-00005-of-00008.safetensors",
         "model.layers.43.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
         "model.layers.43.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
@@ -1065,17 +1067,17 @@
         "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
-        "model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00005-of-00008.safetensors",
         "model.layers.50.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
         "model.layers.50.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
         "model.layers.50.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
         "model.layers.50.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
         "model.layers.50.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
         "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.50.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.50.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.50.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.50.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.50.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
         "model.layers.50.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
         "model.layers.50.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
         "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
@@ -1088,75 +1090,75 @@
         "model.layers.50.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
         "model.layers.50.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
         "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
-        "model.layers.51.input_layernorm.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.input_layernorm.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
         "model.layers.53.input_layernorm.weight": "model-00006-of-00008.safetensors",
-        "model.layers.53.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.53.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.53.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.53.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.53.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.53.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.53.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.53.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.53.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
         "model.layers.53.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.53.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.53.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
         "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
-        "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.53.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
         "model.layers.54.input_layernorm.weight": "model-00006-of-00008.safetensors",
         "model.layers.54.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.54.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
@@ -1295,17 +1297,17 @@
         "model.layers.59.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.59.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors",
         "model.layers.6.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.6.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
         "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
-        "model.layers.6.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.6.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
         "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
         "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
         "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
@@ -1341,17 +1343,17 @@
         "model.layers.60.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.60.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.61.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.61.input_layernorm.weight": "model-00006-of-00008.safetensors",
         "model.layers.61.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.61.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.61.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
         "model.layers.61.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.61.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.61.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.61.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.61.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.61.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.61.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.61.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.61.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
         "model.layers.61.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.61.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.61.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
@@ -1364,75 +1366,75 @@
         "model.layers.61.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
         "model.layers.61.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
         "model.layers.61.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
-        "model.layers.62.input_layernorm.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.input_layernorm.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.62.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.63.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
         "model.layers.64.input_layernorm.weight": "model-00007-of-00008.safetensors",
-        "model.layers.64.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.64.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.64.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.64.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.64.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.64.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.64.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.64.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.64.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.64.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.64.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.64.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
         "model.layers.64.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.64.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.64.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
         "model.layers.64.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
-        "model.layers.64.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.64.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.64.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
         "model.layers.65.input_layernorm.weight": "model-00007-of-00008.safetensors",
         "model.layers.65.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.65.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
@@ -1548,29 +1550,29 @@
         "model.layers.69.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.69.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.69.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
         "model.layers.70.input_layernorm.weight": "model-00007-of-00008.safetensors",
         "model.layers.70.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.70.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
@@ -1617,17 +1619,17 @@
         "model.layers.71.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.71.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.71.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.72.input_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.72.input_layernorm.weight": "model-00007-of-00008.safetensors",
         "model.layers.72.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.72.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.72.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
         "model.layers.72.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.72.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.72.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.72.mlp.up_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.72.mlp.up_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.72.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.72.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.72.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.72.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.72.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.72.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
         "model.layers.72.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.72.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.72.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
@@ -1640,75 +1642,75 @@
         "model.layers.72.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
         "model.layers.72.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
         "model.layers.72.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
-        "model.layers.73.input_layernorm.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.down_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.down_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.gate_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.gate_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.up_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.up_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.k_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.k_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.o_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.o_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.q_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.q_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.v_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.v_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.73.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.input_layernorm.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.down_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.down_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.gate_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.gate_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.up_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.up_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.k_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.k_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.o_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.o_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.q_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.q_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.v_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.v_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.74.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.73.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.73.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.74.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
         "model.layers.75.input_layernorm.weight": "model-00008-of-00008.safetensors",
-        "model.layers.75.mlp.down_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.75.mlp.down_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.75.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.75.mlp.gate_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.75.mlp.gate_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.75.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.75.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.75.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.75.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.75.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.75.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.75.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
         "model.layers.75.mlp.up_proj.biases": "model-00008-of-00008.safetensors",
         "model.layers.75.mlp.up_proj.scales": "model-00008-of-00008.safetensors",
         "model.layers.75.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
         "model.layers.75.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.k_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.k_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.o_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.o_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.q_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.q_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.v_proj.biases": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.v_proj.scales": "model-00008-of-00008.safetensors",
-        "model.layers.75.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.75.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.75.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
         "model.layers.76.input_layernorm.weight": "model-00008-of-00008.safetensors",
         "model.layers.76.mlp.down_proj.biases": "model-00008-of-00008.safetensors",
         "model.layers.76.mlp.down_proj.scales": "model-00008-of-00008.safetensors",
@@ -1801,52 +1803,52 @@
         "model.layers.79.self_attn.v_proj.biases": "model-00008-of-00008.safetensors",
         "model.layers.79.self_attn.v_proj.scales": "model-00008-of-00008.safetensors",
         "model.layers.79.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
-        "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
         "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
-        "model.layers.9.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.9.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.9.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
         "model.layers.9.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
         "model.layers.9.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
         "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
         "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
         "model.norm.weight": "model-00008-of-00008.safetensors"
     }
 }
\ No newline at end of file