upload model

README.md

@@ -1,7 +1,7 @@
 ---
-license: apache-2.0
 language:
 - ko
+license: apache-2.0
 library_name: transformers
 pipeline_tag: question-answering
----
+---

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/data/recoteam_583/mlapp/foundation_models/Orion-14B-Base",
+  "_name_or_path": "/data/recoteam_583/sasha/dacon/experiments/output/orion-14b-merged-ss-bm-rbm/checkpoint-153",
   "architectures": [
     "OrionForCausalLM"
   ],
@@ -27,7 +27,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": false,
   "vocab_size": 84608

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff9c4c8bdabf99735601f7871ae9a7ce6ba53037655039b295f2f19399039e9
+size 4878666800

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0defe7155d8f51f0301df10ee2ed676bd5a61afce25c683b4c3e3d8e3957ade6
+size 4718841760

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a871f632e739850345d79471ca64ac75c7d1b0048b951f53e733bac3b116e6d
+size 4823782088

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94f09e5a103e486e9752e3d7ecdd64d9216cfb85b4b09a793cfc2129d940566
+size 4718841792

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d74e1ee7b776fb030d5efcccb1028197414160ef02c0bda356eac032118c37
+size 4823782128

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45955b34d6e8aae65ee5bce79e699539595a2eca5e8d0d2ff655d69ca324e148
+size 4718841792

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4be4cdb2f3d739e6208e70ec4a75ceba38e2e90fd84ca1bd7cf2140d728b130
+size 4823782128

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3af9d8bec5a0eea3236099d1eaa08721ceb0113ebb058eb9b2ff38824e5ced
+size 4718841792

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef4af65208eb0a2a8a42fd0306e292f2df4a86d893da962e18be86ae5d79b37
+size 4823782128

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909a2c589a345399d41854675030558a9958ebbf712ccfeb02833792def2a9cb
+size 4718841792

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85148f510908cc23056da69cfd6f8ff5b4ed2ff8ec2a0e6e353ea799ec13c1eb
+size 4823782128

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741136749da73761658c89aec36d82924f4477d238d8c23610a8d5b29241bccf
+size 3670306240

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fef2f9b7e19821bc586a421ff755a41fa752cf6e9ab820d6ff57a1a5982215
+size 1732771968

model.safetensors.index.json

@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_size": 57994813440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.38.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.norm.bias": "model-00012-of-00013.safetensors",
+    "model.norm.weight": "model-00012-of-00013.safetensors"
+  }
+}