Upload models

README.md

@@ -0,0 +1,3 @@
+---
+license: cc-by-nc-sa-4.0
+---

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 46336
+}

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": "4.31.0"
+}

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612c50a67a7e878080fdb46a86cd7850e0d47d658299a2ebf4159b627bb6a637
+size 899696928

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb4543d80c3873ce9bc230832ce3919e422b2e5e2dbec1f9798f75b4cdd68a2
+size 989891416

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a6132afc3095ce9be46b217962663c56dccf59c6d1b84fff0c60f15764483b
+size 989891408

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae894011ebe8cc21975512088e9b25f412f196ded9c050002e8c1ba170d6756
+size 989908024

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4369713dffc6d163a2dcd723d581d11c753a8038d90c3508df207170920a0507
+size 956337688

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330cc3171df6bb7b8981a68c56380ffa287c1e95ada5f36755c83ded7bcb0298
+size 989891432

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d68f2ff76244ad2b01054222f3c7b92a171bc63d1de93c4df5ec76a8b37833
+size 989891432

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425a4d1a1bc859358c90a8f3903336fd8f6f3499274b87cda2e677fc92dd5b07
+size 989908048

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c933d9dd80f64a27712eb91574b68a960ef01e4b2d72b219c0fbdb8d96afdb
+size 956337712

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8103b3fdf3f58eae6fb6f7eaf5f522735dae542f2a6406ce807db731dbe17b6a
+size 989891432

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5bcdceb83145eb0312fdfcd497545db6fa8ba16f5930b040f97ff7a115ea08
+size 989891432

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7759b558496fb422ade87ef481d15379436c38994480646fb52fef5ae40fc3a
+size 989908048

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bfd6cbc0beff1ce6c1ec9ff46f1d22ed28489d18ff53cb589b86512512eba8c
+size 956337712

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ebf1f3ff6221b2bdfeccde5c1984940fa7cfa25c485523311791c2899cadca
+size 989891432

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716c83f70bd21abcc97b70cd99fedfe805351e87ee011c741973644ca8967fac
+size 989891432

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2f99831d1fd4b25346958913561f79b8a8163888f7159d748dd5a9f990d50e
+size 989908048

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7dfa95155eceef1fc53883bf75cd0fbc4f8359457674042a6eac729854785f
+size 956337712

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b043b63f6f35ddf1be8142079648c7e1445007bfcf702896aa7582a005d27e1
+size 989891432

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae0dd5c187145212cc44b07dc789edae86d6e53454190dd1aa97d5b07647e7d
+size 989891432

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa68f12298a97ce87df378fedd558bec4f2e9be81ed4e0fe4945a62d90b72f4
+size 989908048

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16668c88c1287db05b6ea11b4994b37198a2d88d09af9c880af4c5fcb01cea07
+size 956337712

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f42ddf453f1f78e3a810a21d3cdf0e164670c3e0ad8ca9e09fc5dccbcf2f4f
+size 788572184

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b1af75755e5eb4d7a08ad92a274b0b8ed1d59190dd7ee24cf3726bcc44e408
+size 379584640

model.safetensors.index.json

@@ -0,0 +1,490 @@
+{
+  "metadata": {
+    "total_size": 21697941504
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00023-of-00023.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00023.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00023.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00023.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00023.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00023.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00023.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00005-of-00023.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00006-of-00023.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00023.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00023.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00006-of-00023.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00023.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00007-of-00023.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00023.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00023.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00007-of-00023.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00023.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00008-of-00023.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00008-of-00023.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00023.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00009-of-00023.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00009-of-00023.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00023.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00023.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00009-of-00023.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00023.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00002-of-00023.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00010-of-00023.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00023.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00023.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00010-of-00023.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00023.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00011-of-00023.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00023.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00023.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00011-of-00023.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00023.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00012-of-00023.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00012-of-00023.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00023.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00013-of-00023.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00013-of-00023.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00023.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00023.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00013-of-00023.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00023.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00014-of-00023.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00023.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00023.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00023.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00023.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00023.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00023.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00014-of-00023.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00023.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00015-of-00023.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00016-of-00023.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00023.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00015-of-00023.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00023.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00016-of-00023.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00016-of-00023.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00023.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00017-of-00023.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00017-of-00023.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00018-of-00023.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00023.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00017-of-00023.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00023.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00018-of-00023.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00019-of-00023.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00019-of-00023.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00018-of-00023.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00023.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00003-of-00023.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "model-00019-of-00023.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00020-of-00023.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00020-of-00023.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "model-00019-of-00023.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00023.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "model-00020-of-00023.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "model-00020-of-00023.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00023.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "model-00021-of-00023.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "model-00021-of-00023.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00022-of-00023.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00023.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "model-00021-of-00023.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00023.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "model-00022-of-00023.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00022-of-00023.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00023.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00023.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00003-of-00023.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00023.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00004-of-00023.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00004-of-00023.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00023.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00005-of-00023.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00023.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00005-of-00023.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00023.safetensors",
+    "model.norm.weight": "model-00022-of-00023.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}