Upload model

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/raid/ngoanpv/finetuning/LLaMA-Factory/exps/yi34b/ngoanyi_44000",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 64000
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4648a02f5e0c500aba23c7bbac25b4485433ec40892e47d106e56f633b892e
+size 9586265368

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03d6261783b1f4bdd9e73b1006de20b1a77d286fe6e6104cf0cad600e052e73
+size 9512923644

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8a468afc0f9075d2ef5f0e10d5e79181c39ab299d3e6fe4aba49eb734d0a0e
+size 9982745124

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2d4c00137ca943d3521912e4b736d79e636da6d72bbf9b42e463f41e1b9004
+size 9512923780

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6182d43d9e8dc5debfe78bc559409e189c7f7a7695c5b6edf9ef861b87083e6a
+size 9512923708

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58da0aeaa2e44c0f87a5899a20b75e6b6eed39923e9ac87d554f76bf03d38276
+size 9982745188

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d2c415a22c0c6ed60b1bc6387b83fc204ea43dfe0a88a267b4809a74bab964
+size 9512923780

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a79f2359a4b8aa9e4d5ea9f052b54e76134b5cc06aa1f334f6d1aab6bef839b
+size 9512923708

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e19f37d2df3e3fa6a7e378e9c744d7bba52197f2d8f248c6593a62939d93c81
+size 9982745188

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0b10eef37a709a430cc7718293c2eb369be94ac43e94102e60ba4d90f14404
+size 9512923780

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2adad0813d431458e0bbe66e71235923fb9a42869380fb7bb5a3587738bd7d1c
+size 9512923708

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3af1ec43ee05bcb5f54338b5769ca249f14d2b040136ca883124313f7d8c9c3
+size 9982745188

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a10eb8f16d844b2f299c509d5c8073fe1a90401ff68a7fd09b0a80c6036b31
+size 9512923780

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad399f8c1d3a2bdb7f8ff2c7efcc226dd45510defa0ef820ed8280f1e896c267
+size 9512923708

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb1a6eccaf61dd341a31c27b68c73eabc846e26baa5f74222fb318a5b752ebe
+size 587290872

pytorch_model.bin.index.json

@@ -0,0 +1,549 @@
+{
+  "metadata": {
+    "total_size": 135720660992
+  },
+  "weight_map": {
+    "embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.10.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.12.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.13.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.16.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "layers.17.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.20.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "layers.21.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.25.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "layers.26.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.29.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "layers.30.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.33.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.33.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "layers.34.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.38.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.38.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.38.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.38.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.38.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "layers.39.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.4.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.40.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.40.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.42.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.42.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.42.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.42.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "layers.43.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.44.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.46.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.46.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.46.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "layers.47.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.48.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.49.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.50.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.51.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.51.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.51.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.51.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.51.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "layers.52.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.52.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.53.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.55.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.55.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.55.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.55.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "layers.56.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.56.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.57.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.58.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.59.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "layers.59.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.59.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.7.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "layers.8.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "norm.weight": "pytorch_model-00015-of-00015.bin"
+  }
+}