Upload LlamaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "chargoddard/Yi-34B-Llama",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d636bb444182909dea61c3ee1eef2aa8ef1f2a04f842c459b89dc8598a3d443
+size 9975341688

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b9d6f2db43299e0cf8ef3c7f1aa314c9cb03039c7e500b4f347f8133dd28fb
+size 9909310352

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6cfcc472bca03a43f5afa12cefc2aace9954d10eb502411f8b50d271aa5ef4
+size 9747800992

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4438a70741ea40778d17e8e3a7104b96c447732a7b3ed6d24ca00102cbbdd8
+size 9747829904

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e83c599a86ce812a96f3b6455762dcefba0fbc98ea2d4f2345307d101affa5
+size 9747829904

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdae3a37b448ec7361d5b1ffcfd10b3936d8f5904fdfbb635b4d73f0c9efc84
+size 9938670728

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d09202b86eaca9aeeec34f42a49ea1c112a7a2b4767b5a69c099aee7179f12
+size 9711114320

model.safetensors.index.json

@@ -6,541 +6,541 @@
     "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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-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-00004-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.v_proj.weight": "model-00003-of-00007.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.26.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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.post_attention_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",