Add model weights

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "nvidia/OpenMath-Llama-2-70b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfbb5d758d71c7f667850e1dc93222b0bece2a89cd212a3748fd35b1978d07c
+size 9852589864

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0acba56ed20996c3294420181d15256408b7b327085582de1ffb607bfb996086
+size 9798096920

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164de8d094c6ffcfae403f7a0fe93368a43ba1c00ae07d488beb686af9b3c8e5
+size 9965868768

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a82a4c996b1c6253f611e43fe5b7d58a450a9668068b9fb33e0e1093035a48a
+size 9798063960

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0c7adafe4ed36c89170d51ef9ca53447be429b2a4e97b89e8aa224d853d66e
+size 9798096960

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b64e2b990fa65c5655aeaee1e9653a653b335d696fe47b9b5e969b49a73dc7a
+size 9798096960

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67065a3cd2c4b782eba7864bdf7dae3364b1a76bb5c7e5a7b8eacdea9631289d
+size 9965868768

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84412569e1cbd3410b78e2a0486b8722330d69290e188c8626147dc630d85df1
+size 9798063960

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0e5c6972ec1ae5b326cf993c21f33a29ee3aa35e1f99c472b62cf3a4e7930a
+size 9798096960

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12641097592754a8ee8611e4c767c9b42ad8e655ef9b0d0d448311a1b750124
+size 9798096960

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef416e045ecfa97d3a3588753381c68d643afa70fce187ea676542968551d88
+size 9965868768

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc1e19c64a200626c607979cd6d1e3492c07b04ab5a845176549dda4c36aef6
+size 9798063960

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e1b6a4f15d467855ece4c88a11feb1b9745e6cf028567e818132d36e80e03a
+size 9798096960

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31668e92bbd150f5df5764e5d162b098f1f56471c434404feee1fb830de8bec
+size 9496123072

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7c3997249bde12a542204a0d8cb2730c2c358df966be8ceee22ad2e5c57377
+size 524288128

model.safetensors.index.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}