Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "yi-34b-200k-dequantized",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d722b3242a2f186cab372303fb877ab74109667a332906a236b51eebda21541f
+size 3971017568

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1e51648ce79a0ad616a70dc3ae454693b2fe281f5f41f22bbc302d0462774f
+size 3875655536

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0caf37886c56e3d9f4857126c84a0ca132ae6de3227b7ba35b42fbeb2550066
+size 3934346536

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457e47a0b9cc50330b28cdfd9e57cff9d40ef6d0454b0ab0f474ff75186af354
+size 3875655568

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaca2f9892b2892df538498df79b27f9ddb4e625f41e5f80db099e8dd3762319
+size 3934346568

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bda9acb5c9eb4d09d6deed4ec18c976bde0369c75f44b89b5d56f7ca6994db4
+size 3875655576

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5ecf68d0d2abef5f2963fcce379f1e09776945541cfffcfc149b88d4ea85b9
+size 3934346568

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702aabf99800f868c031f53759e9d423d218add0b30576c4cf2ae30c2e86c2f0
+size 3875655576

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9746a36a20c29f954582e4076c345c86d24c277dc66192d5ce6e5165ad45aeb4
+size 3934346568

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487bbbdabcd1f821c0ec0bc25b77dfdb09af182991f688728df1a4dff0586777
+size 3875655576

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c03c9011b164d8b45e8099fecf23530ef2056c539375ff5f370b8a3863faf9
+size 3934346568

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e5010eeaff4c2960ffe2e6743a672d0a665df13a45e04e8ea0355982435801
+size 3875655576

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b93bed8a15c675189f68428304e87ff1fd55005d23c498a82488a11c84a0df
+size 3934346568

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ba9e2d46aa1d1e2145556cc499c8ce7688d7265acddd81027838b67d37c157
+size 3875655576

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09a1265a5674e9a381fbcce65663c31bbeba3aea9cf21af0c680f6716d7fadb
+size 3934346568

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33601c7201b0010ab48be715eeb257daff98543ffdfa9f1e075337f120b4ee6
+size 3875655576

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22ba7e7830d99a3260a1a99444afd86a2f6d11c1042ca4f732b6b33c330695b
+size 3934346568

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e34015e9cd175dd4449f20ad518403d983c5da821331d07c486dd1fe5af5dee
+size 2326863440

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00018-of-00018.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.norm.weight": "model-00018-of-00018.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}