初始化项目，由ModelHub XC社区提供模型

Model: sbintuitions/diafill-llm-jp-3.1-13b-instruct4 Source: Original Platform
2026-08-01 17:47:18 +08:00
commit 894f82e1c6
22 changed files with 399249 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,107 @@
+---
+license: apache-2.0
+language:
+  - ja
+pipeline_tag: text-generation
+base_model:
+  - llm-jp/llm-jp-3.1-13b-instruct4
+tags:
+  - dialogue-generation
+  - spoken-dialogue
+---
+
+# diafill-llm-jp-3.1-13b-instruct4
+
+## Model Summary
+**DiaFill** is a Japanese dialogue script generation model designed to produce natural, spoken-style dialogue scripts rich in fillers and brief utternaces.
+Unlike typical assistant models that respond to users, this model is fine-tuned to **generate a multi-turn dialogue script between two speakers** based on a given scenario (seed data).
+
+## Training Data
+This model was fine-tuned on non-public Japanese dialogue script data created as part of the GENIAC (Generative AI Accelerator Challenge) project.
+The training data itself is not publicly available.
+
+The project is described in the following press release:
+https://www.softbank.jp/corp/news/press/sbkk/2025/20250213_01/
+
+
+## Usage (Dialogue Script Generation)
+
+This model generates a dialogue script based on a "Seed" prompt describing the genre, topic, and speakers.
+
+### Input Data Specification
+- **genre**: Choose one of the following Japanese strings:
+    * `雑談` (Chit-chat)
+    * `コールセンター（手続き）` (Call Center - Procedure)
+    * `コールセンター（テクニカルサポート）` (Call Center - Technical Support)
+    * `コールセンター（カスタマーサクセス）` (Call Center - Customer Success)
+- **industry**: Required only for Call Center genres (e.g., "家電", "通信"). **Omit this field if the genre is `雑談`.**
+- **tone**: Basically, choose either フランク (Casual) or 丁寧 (Polite) for each speaker.
+
+### Python Code Example
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
+
+model_name = "sbintuitions/diafill-llm-jp-3.1-13b-instruct4"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+set_seed(42)
+
+seed_data = {
+    "topics": ["家電保証", "修理依頼", "延長保証"],
+    "genre": "コールセンター（手続き）",
+    "industry": "家電",
+    "speaker1_name": "田中",
+    "speaker2_name": "鈴木",
+    "speaker1_tone": "フランク",
+    "speaker2_tone": "丁寧",
+    "summary": "カスタマーは、家電保証に関する手続きについて問い合わせた。オペレーターが修理依頼や延長保証に関する詳細を案内し、カスタマーは納得して対応を依頼した。",
+}
+
+messages = [
+    {"role": "user", "seed": seed_data},
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_tensors="pt",
+).to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        repetition_penalty=1.1,
+    )
+
+generated_script = tokenizer.decode(
+    outputs[0][inputs.shape[1] :],
+    skip_special_tokens=True,
+)
+print(generated_script)
+```
+
+### Generation example
+```
+オペレーター: お電話ありがとうございます。
+カスタマー: いただきます。はい。えっと実はあのー鈴木と申しまして、え今日、例えば、えーっとー電気店の方で、あのーま家族がえ電化製品のですね、えーあのー購入した商品について、まずあの今購入してから3ヶ月ぐらいなんですねんでもそれ以降にその本体の中でこ動かなくなるものがございますので、そういった場合でもそちらの方に連絡したら、すぐまーあのー対応できるようになるのかをお伺いしたいです。
+オペレーター: はい。かしこまりました。では恐れ入ります保障のま内容によって少し変わってくるかと思いますので、一旦ご案内させていただく前に資料確認いたします。お電話切らずに少しお待ちください。保留にいたしますねお客様大変お待たせいたしました。
+カスタマー: 恐れ入ります。
+オペレーター: はいえもう一度確認しますので恐れ入ります。度々、申し訳ございません。申し訳ございませんお待たせしております。恐れ入りますが保障につきましてはもう一つ弊社ですね延長保証がございました。こちらの方がちょっとご説明いただいてなかったかもしれませんので改めてお話させていただきます。こちら月額550円で延長保証となりますので、この分お支払いいただき、されていれば、基本的に故障については修理となります。まずはいどうぞ
+カスタマー: わかりましたじゃ今後はその延長保証にま申し込んでおけば、今回のようなケースに対しても、その電気屋さんの方ですとかあるいはそのメーカーさんの方でも、うそういった形になるということなんですね。
+オペレーター: はいさようでございますおっしゃる通りでございます。私からの案内以上となりますが、他にご不明点ございますか？
+カスタマー: え特にないですよ大丈夫ですよ。はい。それでまた何かありましたらあのーお問い合わせしますので。
+オペレーター: 承知しましたいつでも結構ですので連絡ください。また後でお電話お待ちしておりますよろしくお願いします。田中がご案内いたしました。失礼いたします。
+カスタマー: まはいはい。わかりました承知しました。はい。
+```
+
+## License
+
+[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,46 @@
+{{ bos_token }}
+
+{% for message in messages %}
+{%- set speaker1_label = '話者1' -%}
+{%- set speaker2_label = '話者2' -%}
+{%- if message.get('seed') and message['seed'].get('genre') and 'コールセンター' in message['seed']['genre'] -%}
+{%- set speaker1_label = 'オペレーター' -%}
+{%- set speaker2_label = 'カスタマー' -%}
+{%- endif -%}
+
+{%- if message['role'] == 'user' %}
+### 指示:
+以下の情報に基づいて、日本語の会話文をフィラーなども含めながら、音声での会話として自然な感じで生成してください。
+
+【トピック】
+{{ message['seed']['topics'] | join(', ') }}
+
+【会話ジャンル】
+{{ message['seed']['genre'] }}
+
+{% if message['seed'].get('industry') %}
+【業界カテゴリ】
+{{ message['seed']['industry'] }}
+
+{% endif %}
+【話者情報】
+{{ speaker1_label }}の名前: {{ message['seed']['speaker1_name'] }}
+{{ speaker2_label }}の名前: {{ message['seed']['speaker2_name'] }}
+{{ speaker1_label }}の話し方: {{ message['seed']['speaker1_tone'] }}
+{{ speaker2_label }}の話し方: {{ message['seed']['speaker2_tone'] }}
+
+{% if message['seed'].get('summary') %}
+【会話要約】
+{{ message['seed']['summary'] }}
+
+{% endif %}
+
+{% elif message['role'] == 'assistant' %}
+### 応答:
+{{ message.get('content','') }}
+{{ eos_token }}
+{% endif %}
+{%- if loop.last and add_generation_prompt %}
+### 応答:
+{% endif %}
+{% endfor %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "use_cache": false,
+  "vocab_size": 99584
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.53.0"
+}
--- a/latest_checkpoint.pt
+++ b/latest_checkpoint.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784f5a151026861a376bc4765ea83ff5a374f26f5eaba89ac6164e01961f18c3
+size 1385
--- a/pytorch_model-00001-of-00012.bin
+++ b/pytorch_model-00001-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d169c4ee99f96e81635e4e5390d72f7187ad80ed00da8ace70daa79d0876715
+size 4996555815
--- a/pytorch_model-00002-of-00012.bin
+++ b/pytorch_model-00002-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca98f680f2c23f27dd231b11a87aecf3fa7820db78b5c07b34d68d50bd7803b
+size 4970427583
--- a/pytorch_model-00003-of-00012.bin
+++ b/pytorch_model-00003-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae60f37e133a1de3b6ffb6fb5f3a9dc8d3e4e5f5eb9b024213602aac8c39b26d
+size 4970427571
--- a/pytorch_model-00004-of-00012.bin
+++ b/pytorch_model-00004-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51074056746ac575f10bc4bcca22975a1c7cb2e87bef329934e9a80048a3412b
+size 4970427571
--- a/pytorch_model-00005-of-00012.bin
+++ b/pytorch_model-00005-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f018f5c70404fd1486e332d6551f0a2b12dde9470603bccd0c10d68b3a1034cf
+size 4970427559
--- a/pytorch_model-00006-of-00012.bin
+++ b/pytorch_model-00006-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95cdf89cfe91ed962a9ef5b57f9d975810156255ced650582db5827f8efea295
+size 4792127967
--- a/pytorch_model-00007-of-00012.bin
+++ b/pytorch_model-00007-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5268b3e546e801dadae18084fe254cc60b2263feda0743d19633995d536c173
+size 4792169627
--- a/pytorch_model-00008-of-00012.bin
+++ b/pytorch_model-00008-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d608656a5dcfd0e0d39c3b4c8b3e79dfd0bd624477986283c572b1b212efeed
+size 4792169663
--- a/pytorch_model-00009-of-00012.bin
+++ b/pytorch_model-00009-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84bde9bc07c08a632328a0edc69f352dcd4a6bcef86944e306e272f6d54fa4ac
+size 4970427583
--- a/pytorch_model-00010-of-00012.bin
+++ b/pytorch_model-00010-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6848ff427da89e075a55d14dce8ec5b9ab0c556dada8a0086c90a4fea8b46fc5
+size 4970427571
--- a/pytorch_model-00011-of-00012.bin
+++ b/pytorch_model-00011-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f1ba878e27e2f3f88f5160e4b4281574ba0c6fb17cdce5875889bfe700c85d
+size 3596769205
--- a/pytorch_model-00012-of-00012.bin
+++ b/pytorch_model-00012-of-00012.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7151c32647aecc2865111e7a9d0904354262e50c9b7d5a909a01012b08f60caf
+size 2039482236
--- a/pytorch_model.bin.index.json
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_parameters": 1713490560,
+    "total_size": 54831697920
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00012-of-00012.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00012.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00012.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00012.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00012.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00007-of-00012.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00008-of-00012.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00009-of-00012.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00010-of-00012.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00011-of-00012.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00012.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00012.bin",
+    "model.norm.weight": "pytorch_model-00011-of-00012.bin"
+  }
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,84 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}