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

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "/data/recoteam_583/mlapp/foundation_models/open-solar-ko-10.7b",
+  "_name_or_path": "/data/recoteam_583/charlie/dacon.git/experiments/output/solar-ko-10b-merged_ss_bm_gm-subm/checkpoint-153",
   "architectures": [
-    "LlamaForCausalLM"
+    "LlamaModel"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -22,7 +22,7 @@
   "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": 46592

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44b0b6b813a4d42093400ba9e01c5c7c24bc23b1a550478b76f2b0c306bf90e
+size 4890694232

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1037e647e79a15f2b92d8c80dbcbc2b28282a975fe0f2ee0c96c563dc183fe
+size 4999812760

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6361fa6679f2d9c2d88cc7e52c754f6ae28c766d76185c768e309fdbfeb4ca
+size 4999812808

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5ff8ab9da898b10aad95fe77a4789d1cd78ef6424394000671c4f31dc4572a
+size 4832007216

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7135a567efc14b3d7764f9ce277b88fe117fe436c5ccbab3fd28a9dd7048243e
+size 4999812808

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f72c6f875fa2d4591430551f7000c8e0b71a65f22fd64019cbc3375527bf52a
+size 4999812808

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec3a23154b22ea816b893e1b3f11e5605b5c6f0105f5b11c3ede71871cb545f
+size 4832007216

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773d55110612f114b3c1efe5be1913cf1ee9ba7522775e71ecb3c6633fcd27ec
+size 4999812808

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c3810671972a35339ade668fa795514ed90a3909909d4effc1ec5f065e235e
+size 3087158696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 42640883712
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.40.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.45.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "norm.weight": "model-00009-of-00009.safetensors"
+  }
+}