Upload model

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./axolotl/output-EEVE-Korean-10.8B-v1.0-KoCommercial-ko_Ultrafeedback_binarized-zephyr/v0.1/",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 40960
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8c8bbab63e05c16085ad164859f8977eabea8f3869907d4936333f477eea74
+size 4798419544

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0f04448a1a4e6fe1cc9036f2ecfe650af5200baf722c8fe7603e605cf9681c
+size 4999812760

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9271f7bca74722ff4f0ca40574244f523e2ea5169ee48fcd960a345793375297
+size 4999812808

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364ff2f4f13c9c02df6149cf3381a30e60ad4b76a4da8b552845feb40b5fe77f
+size 4832007216

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e432c9e441020bf998531890eb285489fb995c6a9b1d42ecaa1ddeaf12a559
+size 4999812808

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65970a87042cbb7d0152f4c44ae799b5f880ba932445888e22701074c9d3e31e
+size 4999812808

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8be9b5759fad0372407aa4d2a938d3f8e7750ab121bce63b44e7cb1c3a39d8c
+size 4832007216

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d13b6be31b575072683eb5e538f14f3775b508bcee2e302737b8adedfa4e8e
+size 4999812808

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87319479f83d23f199f20b224a7bd6caedefdc667d13028c2552e99e67549a83
+size 3087158696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 42548609024
+  },
+  "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"
+  }
+}