add model weights

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "aurelian-v0.5-70b-rope8-32K-fp16",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.1"
+}

model-00001-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e1af4d279f81766fe19aea7a741a6404ac2ea0ccae0c9d9019c11a68a55491
+size 4081125640

model-00002-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe3d37d789ff9ebbe5d5ea16d87409f53303d454c010fbbf51dd980f97a72a5
+size 4060154360

model-00003-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f827c54fd4c4f38aac0ffc3a418e237f74687fa176182fa39dd51eb57c3272
+size 3892381840

model-00004-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d54fc807b96904da02bcc6e829c3bee4e9039e399a6978bc4f349d12f5c6291
+size 4060187352

model-00005-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d18a32420cd2438e099070aaf2ad2038b3357a547a1575431f9bb1a362176da
+size 4026599704

model-00006-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213ecb3569fe079e69b564b1b5a8356a933b9ed193bb1b7d1d19135af7bf5e0d
+size 3892381864

model-00007-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4dac0837857b664301c3fb45d31c301f86edcbed2732d040515edbb32b8ae51
+size 4060187376

model-00008-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaefec01a6283e3019c3e30a15d4a31e64b4afe34cc7b569cfab86d54d82c4c7
+size 4026599712

model-00009-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb61833e92f782d3760f97bf02d8bf2ecaf6618a98b8a3503cbbed42eefbced
+size 3892381864

model-00010-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70eb16f7e497d22dbe081e6070bbc1ad854b2f50a83612305c9af33e0dafc81a
+size 4060187376

model-00011-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabbdac2f15adcab26206b56106bc2d182d8ca709b9987f89ad526d0f9475d99
+size 4026599712

model-00012-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fd25f0aa6515f3259b232ec43af3f84f8f3527481e85b4d2b72feddfb9fc54
+size 3892381864

model-00013-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5b6c8fe559b7671cccd9070cb9baadfb5f6fcbcaffda46d74d8ef29c607d83
+size 4060187376

model-00014-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee7be812a9fb268a80a65d39f47d93b9664a105ac881264df0d73a9131af430
+size 4026599712

model-00015-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fcea79b2bc9f2d7171a2918f283a193a5a2162e67e8afe2411c038ca61b6f9
+size 3892381864

model-00016-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e1d7dfca381b9264e837ca89ad6ff652ee7565dd903b32d0711d3cd228f6d4
+size 4060187376

model-00017-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b9ece369b1379a3dc63cac48fd74350224604eb54ac40e6b5d9736a1dfeb17
+size 4026599712

model-00018-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ae593bfa2eb2ae8400896f9af043a3bb2f1669d3cd658e35fe30b06c20a5f7
+size 3892381864

model-00019-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9c885d8249e895a0ee165c20e306c5aaa43a860eff1879b7fa4fc877c875c3
+size 4060187376

model-00020-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49eb41ae45a9fa3f4ae9f3d44a53b68c30c2c2ac5bd60301fffbf35275101508
+size 4026599712

model-00021-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009d9efc2dd185f3e7fb940f1e6ab2e0ee77acb569bf468a6955ae5583aa8efa
+size 3892381864

model-00022-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd01e4f1d1934c6b433ab16a9bd5748ae457c1ab067f8ee8d555126ff2fea5f
+size 4060187376

model-00023-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7671c1388c940d32886f138ef1b53ebec6775fcbe0364e2d12cc71f5adff8b
+size 4026599712

model-00024-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d47795f627d078084320e2bba098d10339470bf65f46903fdcd786323e77b6
+size 3892381864

model-00025-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1d94fa2e4f01cf426ce43f9da863cbe35ea49a2466243e753946eb73150444
+size 4060187376

model-00026-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043606918bb10d34bc5690cd85a2f112e4cf8a8b8bb5f02ca7dc8291117e2863
+size 4026599712

model-00027-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30a6acca7c203130a3f4d8135a24db67d1f0884ff65d870ea3fd8f761b0c1e4
+size 3892381864

model-00028-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53266a03302e54170c1a53c5cea211a93ace278985625434c163d80debbd04ca
+size 4060187376

model-00029-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb64a759e03417fddceff50199d40fe4ffd72ed45e50afe6272f97592a9893f1
+size 4026599712

model-00030-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8781cc6c2141e087108007393b6e714aa131b58a89d2d886d47a26992728d2ed
+size 3892381864

model-00031-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a22eeaceac247483e804b47b43fcd35ccedff854856e209d6d56ffead3fdc34
+size 4060187376

model-00032-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45024bf19e0b9a428c1a0bfe976a38e67a700b6bcc1160945ab86d1d7734be09
+size 4026599712

model-00033-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00806905060270accefda440ec748c455b1e7e18d3dfb533e5c8e35a978fb9cc
+size 3892381864

model-00034-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9672e0b644d8bbcfeb08dbbbf57d00c7889f1d028b2336ad5f69a52f73d3596
+size 4060187376

model-00035-of-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb699832ad0dcdf1437c39019aabf6ce0fae93b4d5644d0afb390de6b60d0e9
+size 2067841928

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953296384
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00035-of-00035.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00035.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00035.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00035.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00035.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00035.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00035.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00035.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00035.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00035.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00035.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00035.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00035.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00035.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00035.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00035.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00035.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00035.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00035.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00035.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00035.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00035.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00035.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00035.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00035.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00035.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00035.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00035.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00015-of-00035.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00035.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00035.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00016-of-00035.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00035.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00035.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00017-of-00035.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00035.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00035.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00018-of-00035.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00035.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00035.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00035.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00035.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00035.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00019-of-00035.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00035.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00035.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00020-of-00035.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00020-of-00035.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00035.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00021-of-00035.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00021-of-00035.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00035.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00022-of-00035.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00035.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00021-of-00035.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00023-of-00035.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00035.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00022-of-00035.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00024-of-00035.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00024-of-00035.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00023-of-00035.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00025-of-00035.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00035.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00024-of-00035.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00026-of-00035.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00035.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00025-of-00035.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00035.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00035.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00035.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00027-of-00035.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00027-of-00035.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00026-of-00035.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00028-of-00035.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00028-of-00035.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00027-of-00035.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00029-of-00035.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00029-of-00035.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00028-of-00035.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00030-of-00035.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00030-of-00035.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00029-of-00035.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00031-of-00035.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00031-of-00035.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00030-of-00035.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00032-of-00035.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00032-of-00035.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00031-of-00035.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00033-of-00035.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00033-of-00035.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00032-of-00035.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00034-of-00035.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00034-of-00035.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00033-of-00035.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00035-of-00035.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00035-of-00035.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00035-of-00035.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00035-of-00035.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00035-of-00035.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00035-of-00035.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00034-of-00035.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00035.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00035.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00035.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00035.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00035.safetensors",
+    "model.norm.weight": "model-00035-of-00035.safetensors"
+  }
+}

oobabooga-instruction-template/Aurelian.yaml

@@ -0,0 +1,24 @@
+instruction_template: |-
+  {%- set ns = namespace(found=false) -%}
+  {%- for message in messages -%}
+      {%- if message['role'] == 'system' -%}
+          {%- set ns.found = true -%}
+      {%- endif -%}
+  {%- endfor -%}
+  {%- if not ns.found -%}
+      {{- '[INST] <<SYS>>\n' + 'An interaction between a user providing instructions, and an imaginative assistant providing responses.' + '\n<</SYS>>\n\n' -}}
+  {%- endif %}
+  {%- for message in messages %}
+      {%- if message['role'] == 'system' -%}
+          {{- '[INST] <<SYS>>\n' + message['content'] + '\n<</SYS>>\n\n' -}}
+      {%- else -%}
+          {%- if message['role'] == 'user' -%}
+              {{-'' + message['content'] + ' [/INST] '-}}
+          {%- else -%}
+              {{-'' + message['content'] + ' </s><s>[INST] ' -}}
+          {%- endif -%}
+      {%- endif -%}
+  {%- endfor -%}
+  {%- if add_generation_prompt -%}
+      {{-''-}}
+  {%- endif -%}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}