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

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/data/recoteam_583/charlie/finetuned_models/qwen-14b-merged_ss_bm_gm-subm/checkpoint-153",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 35,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c3df5a39ea9fda264d65c3820fbfc0fd40315bff4befdce5d87864d407016a
+size 4794779768

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d24fc8c7e1be5516db5316d8971eb074a7277b6b52650e34a205597aae6e737
+size 4939207616

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acd576d8d4e14812c7c32ec740ea1956375040cdd85cd40ff5f487d3b4d5961
+size 4939187032

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3e5afca52676ef4df1b54b23264147dcb442b5ad32951af3c74ec41bc1f749
+size 4939187072

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c5c95abc351b895ffd2eac14f1dead75251eef7aefb2dba1eb803b2b2cf00d
+size 4939187080

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866f4180cc4cdd4d645d0a7d457190d55b5a32d173857d2f5bd2357ef7dbcc53
+size 4763530008

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7af3bba25efe811b65c487b7779e30986a06e76178e094671e88182f3769bb9
+size 4763571184

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63acdb83982483eca1c4c7e4bf66c6f61a46143527c34ce8e14e0b62d02c558a
+size 4763571184

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a57397e4308df18e663e2f61abd5dedda839e482d42fe0f9b39061b0b7ce14
+size 4939207664

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d949d9ed3706088b6d37f4e0315668556e828131703a41374c101746376aa8
+size 4939187080

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014e34c9a8601dd4ae8563c9016857b6eb2c82cfa08e693f12586f1bdbc14677
+size 4834329344

model.safetensors.index.json

@@ -0,0 +1,489 @@
+{
+  "metadata": {
+    "total_size": 53554892800
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00011.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "layers.17.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.20.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "layers.21.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.24.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "layers.25.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.28.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.28.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.28.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.28.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "layers.29.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.32.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.32.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.32.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.32.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "layers.33.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.36.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.36.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.36.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "layers.36.self_attn.v_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.k_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.q_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.v_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.k_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.q_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.v_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.k_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.q_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.v_proj.bias": "model-00011-of-00011.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "norm.weight": "model-00011-of-00011.safetensors"
+  }
+}