Upload model.safetensors.index.json with huggingface_hub

model.safetensors.index.json

@@ -17,23 +17,11 @@
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
     "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00017.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
     "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
@@ -77,11 +65,11 @@
     "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
     "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00017.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
     "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
@@ -125,11 +113,11 @@
     "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
     "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00017.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
     "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
@@ -149,18 +137,18 @@
     "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
     "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00017.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00006-of-00017.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
@@ -185,11 +173,11 @@
     "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
     "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00017.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
@@ -233,11 +221,11 @@
     "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
     "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00017.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
     "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
@@ -281,23 +269,23 @@
     "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
     "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00017.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
     "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
@@ -341,11 +329,11 @@
     "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
     "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00010-of-00017.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
     "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
@@ -389,11 +377,11 @@
     "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
     "model.layers.37.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
     "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00011-of-00017.safetensors",
     "model.layers.38.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
     "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
     "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
     "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
@@ -413,18 +401,18 @@
     "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
     "model.layers.39.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
     "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
     "model.layers.40.input_layernorm.weight": "model-00011-of-00017.safetensors",
     "model.layers.40.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
     "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
@@ -449,11 +437,11 @@
     "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
     "model.layers.41.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
     "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00012-of-00017.safetensors",
     "model.layers.42.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
     "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
     "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
     "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
@@ -497,11 +485,11 @@
     "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
     "model.layers.45.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
     "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00013-of-00017.safetensors",
     "model.layers.46.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
     "model.layers.46.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
     "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
     "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
@@ -545,23 +533,23 @@
     "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
     "model.layers.49.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
     "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.50.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00014-of-00017.safetensors",
     "model.layers.50.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
-    "model.layers.50.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
-    "model.layers.50.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
-    "model.layers.50.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
     "model.layers.50.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
     "model.layers.50.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
     "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
@@ -605,11 +593,11 @@
     "model.layers.53.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
     "model.layers.53.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
     "model.layers.53.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
-    "model.layers.54.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00015-of-00017.safetensors",
     "model.layers.54.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
-    "model.layers.54.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
-    "model.layers.54.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
-    "model.layers.54.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
     "model.layers.54.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
     "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
     "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
@@ -653,11 +641,11 @@
     "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
     "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
     "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
-    "model.layers.58.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00016-of-00017.safetensors",
     "model.layers.58.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
-    "model.layers.58.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
-    "model.layers.58.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
-    "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
     "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
     "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
     "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
@@ -677,18 +665,18 @@
     "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
     "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
     "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
     "model.layers.60.input_layernorm.weight": "model-00016-of-00017.safetensors",
     "model.layers.60.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
     "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
@@ -713,11 +701,11 @@
     "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
     "model.layers.61.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
     "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
-    "model.layers.62.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00017-of-00017.safetensors",
     "model.layers.62.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
-    "model.layers.62.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
-    "model.layers.62.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
-    "model.layers.62.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
     "model.layers.62.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
     "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
     "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
@@ -737,6 +725,18 @@
     "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
     "model.layers.63.self_attn.v_proj.bias": "model-00017-of-00017.safetensors",
     "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",