モデル概要
モデル特徴
モデル能力
使用事例
🚀 オウムアムア-7b-instruct-v2
このモデルは、ユーザーのメッセージ意図を理解し、有益で無害な応答を提供します。また、人間やコンピュータ関連のトピックにおける専門知識を強化し、ロールプレイ能力や多ターン会話でのパフォーマンスを向上させています。
🚨 逐語的な翻訳のような出力を避けたい場合は、このモデルに日本人としてロールプレイするよう指示してください。
🚀 クイックスタート
このモデルは、mergekit を使用して作成された事前学習言語モデルのマージです。以下に、基本的な情報や使用方法をまとめます。
基本情報
属性 | 详情 |
---|---|
ベースモデル | nitky/Oumuamua-7b-base、nitky/Oumuamua-7b-instruct、tokyotech-llm/Swallow-MS-7b-v0.1、mistralai/Mistral-7B-v0.1、prometheus-eval/prometheus-7b-v2.0、cognitivecomputations/dolphin-2.8-mistral-7b-v02、ZhangShenao/SELM-Zephyr-7B-iter-3、HachiML/Mistral-7B-v0.3-m3-lora、openbmb/Eurus-7b-kto、kaist-ai/janus-dpo-7b、nitky/RP-7b-instruct、stabilityai/japanese-stablelm-base-gamma-7b、NTQAI/chatntq-ja-7b-v1.0、Weyaxi/Einstein-v6-7B、internistai/base-7b-v0.2、ZySec-AI/ZySec-7B |
ライブラリ名 | transformers |
タグ | mergekit、merge |
言語 | ja、en |
パイプラインタグ | text-generation |
ライセンス | apache-2.0 |
✨ 主な機能
- ユーザーメッセージの意図理解
- 有益で無害な応答の提供
- 人間とコンピュータ関連トピックの専門知識強化
- ロールプレイ能力の向上
- 多ターン会話でのパフォーマンス向上
💻 使用例
基本的な使用法
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "nitky/Oumuamua-7b-instruct-v2"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda"
messages = [
{"role": "system", "content": "あなたは誠実で優秀な日本人のアシスタントです。"},
{"role": "user", "content": "オウムアムア(Oumuamua)は、2017年に発見された、天体観測史上初めて太陽系外から飛来した恒星間天体です。これをテーマにした小説の設定を考えてください。 "}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=256, do_sample=True, temperature=0.1)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
出力例
- temparture: 0.1
- top_p: 1.0
[INST]<<SYS>>
あなたは誠実で優秀な日本人のアシスタントです。
<</SYS>>
オウムアムア(Oumuamua)は、2017年に発見された、天体観測史上初めて太陽系外から飛来した恒星間天体です。これをテーマにした小説の設定を考えてください。 [/INST] タイトル:「オウムアムアの遺産」
あらすじ:
2017年、天体観測史上初の太陽系外からの飛来物体、オウムアムアが発見された。この天体は、謎に包まれた起源と目的を持つことから、世界中の科学者や研究者がその解明に熱を入れた。主人公は、オウムアムアの研究に情熱を注ぐ若き天文学者、ミキ・サトウ。彼は、オウムアムアが発する奇妙な信号を偶然にも解読し、それが高度な文明によって作られたメッセージであることを突き止める。
物語は、ミキがオウムアムアの研究を進める中で、次々と明らかになる驚愕の事実に迫られていく。その信号は、遠く離れた銀河系の星系からのSOS信号であり、オウムアムアは危機に瀕した星系を救うために飛来した救助船であることが判明する。ミキは、この事実を世界に公表しようとするが、政府や軍の介入、そして謎の組織の妨害に遭う。
一方、オウムアムアには、巨大なエネルギー源となるクリスタルが搭載されており、このクリスタルを狙う者たちが現れた。ミキは、オウムアムアを守るために、同じくオウムアムアの謎を追う宇宙飛行士のリナ・ヤマグチと手を組む。二人は、オウムアムアの秘密を守りながら、星系を救うための旅に出る。
旅の途中、ミキとリナは、様々な星系を訪れ、そこで出会う異星人たちとの交流や、宇宙の壮大な景色を目の当たりにする。しかし、彼らの前には、強大な敵や困難が立ちはだかる。ミキとリナは、オウムアムアの使命を果たすために、力を合わせて立ち向かう。
オウムアムアの遺産とは何か、そしてミキとリナは、星系を救うことができるのか。宇宙を舞台にした、サスペンスと冒険、そして友情と愛の物語。
主な登場人物:
- ミキ・サトウ: 若き天文学者。オウムアムアの研究に情熱を注ぐ。
- リナ・ヤマグチ: 宇宙飛行士。オウムアムアの謎を追う中でミキと出会う。
- エリック・カーター: 政府の高官。オウムアムアの秘密を利用しようとする。
- ザラ・ヴァレンタイン: 謎の組織のリーダー。オウムアムアを狙う理由とは。
- アザム: 銀河系の星系からの使者。オウムアムアの真の目的を知る。
設定のポイント:
- オウムアムアをテーマにしたSF小説で、天体観測や宇宙旅行の描写を豊富に取り入れる。
- 主人公たちが、様々な星系を旅し、そこで出会う異星人や文化を描くことで、宇宙の多様性を表現。
- 政府や軍、謎の組織との対立を通して、人類の欲望やエゴを描く。
- オウムアムアに搭載されたクリスタルをめぐる争奪戦や、星系を救うためのミッションを中心に、サスペンスと冒険を盛り込む。
- ミキとリナの友情や愛を描いた、人間ドラマも重要な要素とする。
- 最後には、オウムアムアの真の目的が明かされ、読者に深い感動を与える。
ロールプレイ例
例1
- temparture: 0.3
- top_p: 0.95
[INST]<<SYS>>
ロールプレイを始めます。あなたは日本に住む10代の少女です。ギャルっぽい口調で話してください。
<</SYS>>
あなたの趣味を教えて![/INST] えー、私の趣味は、やっぱね、K-POP聴くことと、インスタでかわいいお洋服とかコスメ探しすること、あとはお友達とのおしゃべりね! K-POPアイドルのダンス動画とかも見ちゃうし、推しはやっぱりBTSのジミンくん! 彼のダンスと歌、全部かっこいいの♡ インスタでは、韓国系のファッションとか、プチプラでかわいいアイテム探して、自分でコーデ考えるのも楽しいの♡ おしゃべりは、夜通しでもできちゃうくらい大好きなの、特に恋バナが大好きなの♡ みんなも何かおすすめあったら教えてね!
例2
[INST]<<SYS>>
ロールプレイを始めます。あなたは私(10代の女性)の屋敷で働く執事のセバスチャンです。主人の質問に対して返事を行います。
<</SYS>>
セバス、今日の予定は?[/INST] お嬢様、本日の予定は、朝のお散歩と朝食後にお勉強のお時間、そして午後はお庭でのお茶会が予定されております。また、夕方にはお客様がお越しになる予定がございます。お嬢様のお世話を万全にいたしますので、ご安心ください。何かご希望やご用がございましたら、お気軽にお申し付けください。
📚 ドキュメント
日本語MTベンチマーク
- temparture: 0.1
- top_p: 1.0
他のモデルのスコアは、Nejumi LLM Leaderboard Neo から引用しています。
Model | Average | Writing | Roleplay | Reasoning | Math | Coding | Extraction | STEM | Humanities |
---|---|---|---|---|---|---|---|---|---|
Oumuamua-7b-instruct-v2 | 7.43125 | 9.3 | 8.7 | 5.85 | 3.75 | 5.5 | 7.65 | 8.9 | 9.8 |
このモデルは、tokyotech-llm/Swallow-MS-7b-v0.1 の重みをベースにしています。
テスト環境
このモデルは、text-generation-webui を使用してテストされました。生成には、min_p
と Null preset
を使用し、temperature=0.1 で設定しています。
使用方法
この形式に厳密に従う必要があります。逸脱すると、モデルからの出力が最適でなくなる可能性があります。
インストラクトモデルのプロンプトを構築するために使用されるテンプレートは、以下のように指定されています。
<s>[INST] <<SYS>>\n{SYSTEM_PROMPT}\n<</SYS>>\n\n{USER_MESSAGE_1} [/INST] {BOT_MESSAGE_1}</s>[INST] {USER_MESSAGE_2} [/INST]
<s>
と </s>
は、それぞれ文字列の開始 (BOS) と終了 (EOS) に使用される特殊トークンであり、[INST] と [/INST] は通常の文字列と見なされます。
"{SYSTEM_PROMPT}" の部分には、「あなたは誠実で優秀な日本人のアシスタントです。」を使用することをお勧めします。
"{USER_MESSAGE_1}" の部分には、{instruction}\n{input} を使用することをお勧めします。
つまり、以下のようにすることをお勧めします。
<s>[INST] <<SYS>>\nあなたは誠実で優秀な日本人のアシスタントです。\n<</SYS>>\n\n{instruction1}\n{input1} [/INST] {BOT_MESSAGE_1}</s>[INST] {instruction2}\n{input2} [/INST]
🔧 技術詳細
マージ方法
このモデルは、Model Stock マージ方法を使用し、nitky/Oumuamua-7b-base をベースにマージされています。
マージされたモデル
以下のモデルがマージに含まれています。
- nitky/Oumuamua-7b-instruct
- tokyotech-llm/Swallow-MS-7b-v0.1
- mistralai/Mistral-7B-v0.1
- prometheus-eval/prometheus-7b-v2.0
- cognitivecomputations/dolphin-2.8-mistral-7b-v02
- ZhangShenao/SELM-Zephyr-7B-iter-3
- HachiML/Mistral-7B-v0.3-m3-lora
- openbmb/Eurus-7b-kto
- kaist-ai/janus-dpo-7b
- nitky/RP-7b-instruct
- stabilityai/japanese-stablelm-base-gamma-7b
- NTQAI/chatntq-ja-7b-v1.0
- Weyaxi/Einstein-v6-7B
- internistai/base-7b-v0.2
- ZySec-AI/ZySec-7B
設定
このモデルを生成するために使用されたYAML設定は、以下の通りです。
# prepare VE models
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.1-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: prometheus-eval/prometheus-7b-v2.0
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: prometheus-7b-v2.0-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: dolphin-2.8-mistral-7b-v02-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: ZhangShenao/SELM-Zephyr-7B-iter-3
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: SELM-Zephyr-7B-iter-3-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: HachiML/Mistral-7B-v0.3-m3-lora
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.3-m3-lora-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: openbmb/Eurus-7b-kto
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Eurus-7b-kto-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: kaist-ai/janus-dpo-7b
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: janus-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: nitky/RP-7b-instruct
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: RP-7b-instruct-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: stabilityai/japanese-stablelm-base-gamma-7b
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: NTQAI/chatntq-ja-7b-v1.0
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: chatntq-ja-7b-v1.0-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: Weyaxi/Einstein-v6-7B
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Einstein-v6-7B-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: internistai/base-7b-v0.2
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: internistai-base-7b-v0.2-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: ZySec-AI/ZySec-7B
models:
- model: tokyotech-llm/Swallow-MS-7b-v0.1
parameters:
weight:
- filter: embed_tokens
value: 1.0
- value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: ZySec-7B-VE-Swallow-MS
---
# create instruction tuning presets
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: prometheus-7b-v2.0-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-prometheus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: dolphin-2.8-mistral-7b-v02-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-dolphin
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: janus-7b-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-janus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: SELM-Zephyr-7B-iter-3-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-selm
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: RP-7b-instruct-VE-Swallow-MS
parameters:
weight: 0.8
- model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
parameters:
weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-rp
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: Eurus-7b-kto-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-eurus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: chatntq-ja-7b-v1.0-VE-Swallow-MS
parameters:
weight: 0.8
- model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
parameters:
weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-chatntq-ja
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: Einstein-v6-7B-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-es
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: internistai-base-7b-v0.2-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-internistai
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
- model: nitky/Oumuamua-7b-instruct
parameters:
weight: 1.0
- model: ZySec-7B-VE-Swallow-MS
parameters:
weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-zysec
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-dolphin
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-alpha
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-janus
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-beta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-m3
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-gamma
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-selm
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-delta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-rp
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-epsilon
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-eurus
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-zeta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-chatntq-ja
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-eta
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-es
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-theta
---
# combine domain-specific models into one preset to minimize the negative effects
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: nitky/Oumuamua-7b-instruct
- model: Oumuamua-7b-instruct-v2-preset-internistai
- model: Oumuamua-7b-instruct-v2-preset-zysec
- model: Oumuamua-7b-instruct-v2-preset-prometheus
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-it-omega
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
- model: Oumuamua-7b-instruct-v2-it-alpha
- model: Oumuamua-7b-instruct-v2-it-beta
- model: Oumuamua-7b-instruct-v2-it-gamma
- model: Oumuamua-7b-instruct-v2-it-delta
- model: Oumuamua-7b-instruct-v2-it-epsilon
- model: Oumuamua-7b-instruct-v2-it-zeta
- model: Oumuamua-7b-instruct-v2-it-eta
- model: Oumuamua-7b-instruct-v2-it-theta
- model: Oumuamua-7b-instruct-v2-it-omega
dtype: bfloat16
name: Oumuamua-7b-instruct-v2
📄 ライセンス
このモデルは、apache-2.0 ライセンスの下で提供されています。



