commit 6a8188c88d8d770e41939014711a4c9ac60ae43c
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Wed May 13 10:25:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: maywell/PiVoT-SOLAR-10.7B-RP
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..7a0c7c6
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+ 
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+pytorch_model-00003-of-00005.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00005.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00005.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00005.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00005.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/PiVoT.png b/PiVoT.png
new file mode 100644
index 0000000..00231ea
Binary files /dev/null and b/PiVoT.png differ
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..53ea42b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,23 @@
+---
+license: cc-by-sa-4.0
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# PiVoT-SOLAR-10.7B-RP
+
+![image/png](./PiVoT.png)
+
+# **Model Details**
+
+### Description
+PivoT is RP Finetuned model based on SOLAR-10.7B-Instruct. Private RP dataset collected from ArcaLive Ai Chat Chan used.
+
+This model has sequence length of **8192**
+
+Follow me on twitter: https://twitter.com/stablefluffy
+
+Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕
+
+Contact me on Telegram: https://t.me/AlzarTakkarsen
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..e427ff1
--- /dev/null
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "maywell/PiVoT-SOLAR-10.7B-RP",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..5205434
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false
+}
diff --git a/pytorch_model-00001-of-00005.bin b/pytorch_model-00001-of-00005.bin
new file mode 100644
index 0000000..0bdc0ba
--- /dev/null
+++ b/pytorch_model-00001-of-00005.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bb14f443484bf711da924d8981a9fc436a0f9bcfbebb3006e197c205286845
+size 4943185145
diff --git a/pytorch_model-00002-of-00005.bin b/pytorch_model-00002-of-00005.bin
new file mode 100644
index 0000000..5e1cd61
--- /dev/null
+++ b/pytorch_model-00002-of-00005.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7038c5fe0211da7a719ab30a2e68046ed38865df07bbd61aecf984e404d8d86b
+size 4999844257
diff --git a/pytorch_model-00003-of-00005.bin b/pytorch_model-00003-of-00005.bin
new file mode 100644
index 0000000..772aeff
--- /dev/null
+++ b/pytorch_model-00003-of-00005.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c1ceaa80b828e716d6a0fd09820227d527e2b231ca8d617e1971f242516d34
+size 4915939683
diff --git a/pytorch_model-00004-of-00005.bin b/pytorch_model-00004-of-00005.bin
new file mode 100644
index 0000000..77a1426
--- /dev/null
+++ b/pytorch_model-00004-of-00005.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd35ed52f7ada538920f02f0fa866977b063f54543a83367e6d6db1d343af127
+size 4915939683
diff --git a/pytorch_model-00005-of-00005.bin b/pytorch_model-00005-of-00005.bin
new file mode 100644
index 0000000..9e76100
--- /dev/null
+++ b/pytorch_model-00005-of-00005.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa739d85e684c72e65481ef7596c3f6a6478bf1aaff6edeec7e08a8cc3869bd
+size 1688292111
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..80a29ae
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 21463048192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.norm.weight": "pytorch_model-00005-of-00005.bin"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..3a0208d
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..61607de
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc
+size 1795303
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..8b443ef
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..aef4138
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "</s>",
+  "use_default_system_prompt": true
+}