update model

config.json

@@ -17,7 +17,7 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 5000000.0,
+  "rope_theta": 10000000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.34.0",

md5

@@ -1,8 +1,8 @@
-86017adcb3076e243b3f07e38f3b33f3  pytorch_model-00001-of-00007.bin
-0716bd614cd496044594b8fa58888dc1  pytorch_model-00002-of-00007.bin
-5f84d51eef7eb3645cf06a79a1fa2592  pytorch_model-00003-of-00007.bin
-f91ff0e65f5f64c8b7b8c0eb52aa1738  pytorch_model-00004-of-00007.bin
-63f1e78d652c40f06965e3299f01b9e8  pytorch_model-00005-of-00007.bin
-ac4df78c66c31fc3164d06b375aaee4a  pytorch_model-00006-of-00007.bin
-e0fd1a655c86caaaff3ca9252991cc25  pytorch_model-00007-of-00007.bin
+c940c9d45a0ee5879b1f980ecab7c36a  pytorch_model-00001-of-00007.bin
+76ed9d3b168a0c7f6b14f0d581f130d7  pytorch_model-00002-of-00007.bin
+c8856c182b23e8d029e924427a28e54f  pytorch_model-00003-of-00007.bin
+6a8c0d10b3efe52eacf959ce8f851a55  pytorch_model-00004-of-00007.bin
+f735a09eb0a8eb8e5dd22941670741a2  pytorch_model-00005-of-00007.bin
+d0b62d2b1c099bba8dd5ba6691165c1b  pytorch_model-00006-of-00007.bin
+9153494d8705b88c2606b9c05ec1d535  pytorch_model-00007-of-00007.bin
 291724ef50f729e45d68f474a7755bbc  tokenizer.model

model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220cfc345386d852df5fa17bd02ada00817a1008b35de2dfd4a76a59b4af0e1c
-size 9975341688
+oid sha256:9347029a9ae070b3355d39bcf3ca1ea396a3a4688a916f083bc09fc70142c30a
+size 9975343640

model-00002-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bfb29b9b1f25d4d2acc57ec9f934c16fa8305c4798fa4407492dcc7d1ee5c8
-size 9909310352
+oid sha256:6fcd9ae5eae71bca3b900c68abb97efb9125328ad079ed7d04ba3f42e73ee5b0
+size 9909312552

model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7352e5153f801a493b2faa207d4e486dd3c07565bffef4ee5f58d0a2a5670fa2
-size 9747801000
+oid sha256:42c1044a9c80c35d059ff82347d2e05225111e7c04694113bc944ca10b46732e
+size 9747803200

model-00004-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d689009b8e82f60f2c6bbdca079acfd7274179d28639d2030c0e47afd02f47
-size 9747829904
+oid sha256:b5c5bb57cc481666cf240166992606b7331cc1e0692a0e8b4a5fdb4c5bc3e3a0
+size 9747832112

model-00005-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d171f33876b095c0754fdc35a4756bbaafafaf082fe4034f22d78272ceecb15a
-size 9747829904
+oid sha256:6b8b308434d6e5e488da1ecf6cf523fd541f7ded40372cd3601a3a4e37210ada
+size 9747832104

model-00006-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ad53ee6c607d9a0be1b08c4110ec689576daafbb5a635dd58ea4ae44fc9391
-size 9938670728
+oid sha256:851bd26b12e96cfedb18a48629d68816713449e05c496a5e6d4ef4c39991cc5f
+size 9938672688

model-00007-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75710f975c2cfb56d1ed393ed48e06afc3e36dcb7985b886dc489c9e62d7d139
-size 9711114320
+oid sha256:8851d9da1530217397660174eb8cf6dada2d8488d5a30d98f09abe31fe037c22
+size 9711116280

model.safetensors.index.json

@@ -1,550 +1,610 @@
 {
-  "metadata": {
-    "total_size": 68777834496
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00007-of-00007.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.52.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.52.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.52.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.53.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.norm.weight": "model-00007-of-00007.safetensors"
-  }
-}
+    "metadata": {
+        "total_size": 68777842176
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00007-of-00007.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.norm.weight": "model-00007-of-00007.safetensors"
+    }
+}

pytorch_model-00001-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af379d94f156000f8966841e16b6c4c2f70e299ffe978087730aee90a9b6cfd
-size 9975358895
+oid sha256:ac1433f4681f9d5c97d062c7a9355cab5b3b1cd6974375a6c2cc8d4b7aca423e
+size 9975363158

pytorch_model-00002-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f736e1ab0969c981cfeebc6375162c78d336293ce8c349daea0a8831d1086d8a
-size 9909328019
+oid sha256:fcdf6752dfa468a2bd08b5f48af61e1ff514bae70460129d6afa3348b67e6bdf
+size 9909332760

pytorch_model-00003-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5e24f31ea109c5a5d711aa3b4fbb1b79126313a79cf4495e9495d640168294
-size 9747818583
+oid sha256:882d16387f20ca59a073cc2fa96cd78f6b48a7543700c2764ca65104d09c31ce
+size 9747823300

pytorch_model-00004-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b68248f563fefad0b07e1aebcde955b7ccc434ffbe31890aec8033876b10b29
-size 9747847907
+oid sha256:5f03d67d05749105fc2b64b37b900045724229e30ac719fe892e1687c1dae320
+size 9747852648

pytorch_model-00005-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4497cec4c1f012ddc2447e967f72f778744f45dedf1401132e400b0ade756246
-size 9747847967
+oid sha256:9d32924513e317db6b65cd8d90416bc87137492f4c2bede8cf5b359880158f6b
+size 9747852744

pytorch_model-00006-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9b4e09a6858918e4a2a5c0f6c720c5a9bf49de2f97644be9b35ded975289c
-size 9938688835
+oid sha256:87ece1984645327e4b0c8347cb0109d8e282b5a9a392ac2fc52e178f446aa125
+size 9938693098

pytorch_model-00007-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d2472ebcab1f626c85f19850c23f8bdef8463aa5f06e7e7d1932547bffa977
-size 9711130369
+oid sha256:3cb9d3513608875e740dfb5fb3a88867c4df838c90b2b219263da42ae28ebc5e
+size 9711134568

pytorch_model.bin.index.json

@@ -1,549 +1,609 @@
 {
   "metadata": {
-    "total_size": 68777834496
+    "total_size": 68777842176
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00007-of-00007.bin",
     "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
-    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
     "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
     "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
-    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
     "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
     "model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
-    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
     "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
     "model.layers.53.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
-    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
     "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
     "model.norm.weight": "pytorch_model-00007-of-00007.bin"
   }