Amazon Bedrock で利用可能になった Mistral Large で複雑な推論タスクに取り組む

３月、2 つの高性能 Mistral AI モデルである Mistral 7B と Mixtral 8x7B が Amazon Bedrock で使用可能になったことをお知らせしました。Mistral 7B は、Mistral の最初の基盤モデルとして、自然なコーディング機能で英語のテキスト生成タスクをサポートします。Mixtral 8x7B は、テキストの要約、質疑応答、テキストの分類、テキスト補完、コード生成に最適な、人気のある高品質の Sparse Mixture-of-Experts (MoE) モデルです。

4月2日、Amazon Bedrock で Mistral Large が利用可能になったことをお知らせします。Mistral Large は、実質的な推論機能を必要とする複雑なタスクや、合成テキスト生成およびコード生成などの高度に専門化されたタスクに最適です。

Mistral Large について知っておくべきこと:

• 英語、フランス語、スペイン語、ドイツ語、イタリア語でネイティブレベルの流暢さを備えており、文法や文化的背景のニュアンスをよく理解しています。
• 32K トークンのコンテキストウィンドウがあり、サイズが大きいドキュメントからでも正確な情報を取得できます。
• その正確な Instruction Following により、モデレーションポリシーを設計できます。Mistral AI の人々は、ベータアシスタントデモンストレーターである le Chat のシステムレベルのモデレーションを設定するためにこれを使用しました。大規模言語モデル (LLM) との最初のインタラクションは、プロンプトを中心に展開します。効果的なプロンプトを作成する技術は、LLM から望ましい応答を生成するために不可欠です。また、Mistral AI はサンプルプロンプトを含むガイドを提供しており、さまざまなプロンプト機能が示されています。

Mistral Large の開始方法
Bedrock で Mistral Large の使用を開始するには、まずモデルにアクセスする必要があります。Amazon Bedrock コンソールで、[モデルアクセス] を選択してから、[モデルアクセスを管理] を選択します。次に、[Mistral Large] を選択し、[変更を保存] を選択します。

Mistral Large にアクセスできるようになると、Bedrock でモデルを使用できるようになります。更新されたステータスを表示するには、ベースモデルのテーブルを更新します。

Mistral Large の複雑な推論の側面が機能している様子を見るために、[プレイグラウンド] セクションで次のプロンプトを試してみました。

プロンプト

Calculate the difference in payment dates between the two customers whose payment amounts are closest to each other in the given dataset:

'{
"transaction_id":{"0":"T1001","1":"T1002","2":"T1003","3":"T1004","4":"T1005"},
"customer_id":{"0":"C001","1":"C002","2":"C003","3":"C002","4":"C001"},
"payment_amount":{"0":125.5,"1":89.99,"2":120.0,"3":54.3,"4":210.2},
"payment_date":{"0":"2021-10-05","1":"2021-10-06","2":"2021-10-07","3":"2021-10-05","4":"2021-10-08"},
"payment_status":{"0":"Paid","1":"Unpaid","2":"Paid","3":"Paid","4":"Pending"}
}'

出力

To find the difference in payment dates between the two customers whose payment amounts are closest to each other, we first need to identify the two closest payment amounts and then find their respective payment dates.

The payment amounts are: 125.5, 89.99, 120.0, 54.3, 210.2

The two closest payment amounts are 125.5 and 120.0.The payment date for the payment amount 125.5 is '2021-10-05' and for the payment amount 120.0 is '2021-10-07'.

The difference in payment dates can be calculated as follows:

Date difference = |'2021-10-07' - '2021-10-05'| = 2 days

So, the difference in payment dates between the two customers whose payment amounts are closest to each other is 2 days.

私はこの記事の前半で、Mistral Large が複数の言語でネイティブレベルの流暢さを備えており、文法や文化的背景のニュアンスをよく理解していると述べました。そこで、モデルのフランス語の理解度をテストしてみました。

プロンプト

Lequel est le plus lourd une livre de fer ou un kilogramme de plume

出力

Un kilogramme de plumes est plus lourd qu'une livre de fer.

Pour comprendre cela, il est important de se rappeler que :

1.Une livre (lb) est une unité de mesure de masse principalement utilisée aux États-Unis et dans d'autres systèmes de mesure impériaux, tandis qu'un kilogramme (kg) est l'unité de base de masse dans le système international d'unités (SI).

2. 1 kilogramme est approximativement égal à 2,2 livres.

Donc, un kilogramme de plumes est plus lourd qu'une livre de fer, car il correspond à environ 2,2 livres de plumes.

Mistral Large をプログラムで操作する
また、AWS コマンドラインインターフェイス (CLI) と AWS Software Development Kit (SDK) で Amazon Bedrock API を使用してさまざまな呼び出しを実行することもできます。AWS SDK を使用して Amazon Bedrock Runtime API を操作する Python のサンプルコードを次に示します。「You will only respond with a JSON object with the key X, Y, and Z.」(キー X、Y、Z を持つ JSON オブジェクトのみで応答してください) とプロンプトで指定すると、簡単なダウンストリームタスクで JSON 形式の出力を使用できます。

import boto3
import json

bedrock = boto3.client(service_name="bedrock-runtime", region_name='us-east-1')

prompt = """
<s>[INST]You are a summarization system that can provide summaries with associated confidence 
scores.In clear and concise language, provide three short summaries of the following essay,
along with their confidence scores.You will only respond with a JSON object with the key Summary 
and Confidence.Do not provide explanations.[/INST]

# Essay: 
The generative artificial intelligence (AI) revolution is in full swing, and customers of all sizes and across industries are taking advantage of this transformative technology to reshape their businesses.From reimagining workflows to make them more intuitive and easier to enhancing decision-making processes through rapid information synthesis, generative AI promises to redefine how we interact with machines.It’s been amazing to see the number of companies launching innovative generative AI applications on AWS using Amazon Bedrock.Siemens is integrating Amazon Bedrock into its low-code development platform Mendix to allow thousands of companies across multiple industries to create and upgrade applications with the power of generative AI.Accenture and Anthropic are collaborating with AWS to help organizations—especially those in highly-regulated industries like healthcare, public sector, banking, and insurance—responsibly adopt and scale generative AI technology with Amazon Bedrock.This collaboration will help organizations like the District of Columbia Department of Health speed innovation, improve customer service, and improve productivity, while keeping data private and secure.Amazon Pharmacy is using generative AI to fill prescriptions with speed and accuracy, making customer service faster and more helpful, and making sure that the right quantities of medications are stocked for customers.

To power so many diverse applications, we recognized the need for model diversity and choice for generative AI early on.We know that different models excel in different areas, each with unique strengths tailored to specific use cases, leading us to provide customers with access to multiple state-of-the-art large language models (LLMs) and foundation models (FMs) through a unified service: Amazon Bedrock.By facilitating access to top models from Amazon, Anthropic, AI21 Labs, Cohere, Meta, Mistral AI, and Stability AI, we empower customers to experiment, evaluate, and ultimately select the model that delivers optimal performance for their needs.

Announcing Mistral Large on Amazon Bedrock
Today, we are excited to announce the next step on this journey with an expanded collaboration with Mistral AI.A French startup, Mistral AI has quickly established itself as a pioneering force in the generative AI landscape, known for its focus on portability, transparency, and its cost-effective design requiring fewer computational resources to run.We recently announced the availability of Mistral 7B and Mixtral 8x7B models on Amazon Bedrock, with weights that customers can inspect and modify.Today, Mistral AI is bringing its latest and most capable model, Mistral Large, to Amazon Bedrock, and is committed to making future models accessible to AWS customers.Mistral AI will also use AWS AI-optimized AWS Trainium and AWS Inferentia to build and deploy its future foundation models on Amazon Bedrock, benefitting from the price, performance, scale, and security of AWS.Along with this announcement, starting today, customers can use Amazon Bedrock in the AWS Europe (Paris) Region.At launch, customers will have access to some of the latest models from Amazon, Anthropic, Cohere, and Mistral AI, expanding their options to support various use cases from text understanding to complex reasoning.

Mistral Large boasts exceptional language understanding and generation capabilities, which is ideal for complex tasks that require reasoning capabilities or ones that are highly specialized, such as synthetic text generation, code generation, Retrieval Augmented Generation (RAG), or agents.For example, customers can build AI agents capable of engaging in articulate conversations, generating nuanced content, and tackling complex reasoning tasks.The model’s strengths also extend to coding, with proficiency in code generation, review, and comments across mainstream coding languages.And Mistral Large’s exceptional multilingual performance, spanning French, German, Spanish, and Italian, in addition to English, presents a compelling opportunity for customers.By offering a model with robust multilingual support, AWS can better serve customers with diverse language needs, fostering global accessibility and inclusivity for generative AI solutions.

By integrating Mistral Large into Amazon Bedrock, we can offer customers an even broader range of top-performing LLMs to choose from.No single model is optimized for every use case, and to unlock the value of generative AI, customers need access to a variety of models to discover what works best based for their business needs.We are committed to continuously introducing the best models, providing customers with access to the latest and most innovative generative AI capabilities.

“We are excited to announce our collaboration with AWS to accelerate the adoption of our frontier AI technology with organizations around the world.Our mission is to make frontier AI ubiquitous, and to achieve this mission, we want to collaborate with the world’s leading cloud provider to distribute our top-tier models.We have a long and deep relationship with AWS and through strengthening this relationship today, we will be able to provide tailor-made AI to builders around the world.”

– Arthur Mensch, CEO at Mistral AI.

Customers appreciate choice
Since we first announced Amazon Bedrock, we have been innovating at a rapid clip—adding more powerful features like agents and guardrails.And we’ve said all along that more exciting innovations, including new models will keep coming.With more model choice, customers tell us they can achieve remarkable results:

“The ease of accessing different models from one API is one of the strengths of Bedrock.The model choices available have been exciting.As new models become available, our AI team is able to quickly and easily evaluate models to know if they fit our needs.The security and privacy that Bedrock provides makes it a great choice to use for our AI needs.”

– Jamie Caramanica, SVP, Engineering at CS Disco.

“Our top priority today is to help organizations use generative AI to support employees and enhance bots through a range of applications, such as stronger topic, sentiment, and tone detection from customer conversations, language translation, content creation and variation, knowledge optimization, answer highlighting, and auto summarization.To make it easier for them to tap into the potential of generative AI, we’re enabling our users with access to a variety of large language models, such as Genesys-developed models and multiple third-party foundational models through Amazon Bedrock, including Anthropic’s Claude, AI21 Labs’s Jurrassic-2, and Amazon Titan.Together with AWS, we’re offering customers exponential power to create differentiated experiences built around the needs of their business, while helping them prepare for the future.”

– Glenn Nethercutt, CTO at Genesys.

As the generative AI revolution continues to unfold, AWS is poised to shape its future, empowering customers across industries to drive innovation, streamline processes, and redefine how we interact with machines.Together with outstanding partners like Mistral AI, and with Amazon Bedrock as the foundation, our customers can build more innovative generative AI applications.

Democratizing access to LLMs and FMs
Amazon Bedrock is democratizing access to cutting-edge LLMs and FMs and AWS is the only cloud provider to offer the most popular and advanced FMs to customers.The collaboration with Mistral AI represents a significant milestone in this journey, further expanding Amazon Bedrock’s diverse model offerings and reinforcing our commitment to empowering customers with unparalleled choice through Amazon Bedrock.By recognizing that no single model can optimally serve every use case, AWS has paved the way for customers to unlock the full potential of generative AI.Through Amazon Bedrock, organizations can experiment with and take advantage of the unique strengths of multiple top-performing models, tailoring their solutions to specific needs, industry domains, and workloads.This unprecedented choice, combined with the robust security, privacy, and scalability of AWS, enables customers to harness the power of generative AI responsibly and with confidence, no matter their industry or regulatory constraints.
"""

body = json.dumps({
    "prompt": prompt,
    "max_tokens": 512,
    "top_p": 0.8,
    "temperature": 0.5,
})

modelId = "mistral.mistral-large-2402-v1:0"

accept = "application/json"
contentType = "application/json"

response = bedrock.invoke_model(
    body=body,
    modelId=modelId,
    accept=accept,
    contentType=contentType
)

print(json.loads(response.get('body').read()))

次のような JSON 形式の出力を取得できます。

{ 
   "Summaries": [ 
      { 
         "Summary": "The author discusses their early experiences with programming and writing,
starting with writing short stories and programming on an IBM 1401 in 9th grade.
They then moved on to working with microcomputers, building their own from a Heathkit,
and eventually convincing their father to buy a TRS-80 in 1980.They wrote simple games,
a program to predict rocket flight trajectories, and a word processor.",
         "Confidence": 0.9 
      },
      { 
         "Summary": "The author began college as a philosophy major, but found it to be unfulfilling 
and switched to AI.They were inspired by a novel and a PBS documentary, as well as the 
potential for AI to create intelligent machines like those in the novel.Despite this 
excitement, they eventually realized that the traditional approach to AI was flawed and 
shifted their focus to Lisp.",
         "Confidence": 0.85 
      },
      { 
         "Summary": "The author briefly worked at Interleaf, where they found that their Lisp skills 
were highly valued.They eventually left Interleaf to return to RISD, but continued to work 
as a freelance Lisp hacker.While at RISD, they started painting still lives in their bedroom 
at night, which led to them applying to art schools and eventually attending the Accademia 
di Belli Arti in Florence.",
         "Confidence": 0.9 
      } 
   ] 
}

Mistral AI モデルのプロンプト機能の詳細については、Mistral AI のドキュメントにアクセスしてください。

今すぐご利用いただけます
Mistral Large は、他の Mistral AI モデル (Mistral 7B および Mixtral 8x7B) とともに、米国東部 (バージニア北部)、米国西部 (オレゴン)、および欧州 (パリ) リージョンにおいて、Amazon Bedrock で現在ご利用いただけます。今後の更新については、詳細なリージョンのリストをご覧ください。

community.aws で生成 AI コミュニティと共有し、学びましょう。Amazon Bedrock コンソール で Mistral Large を今すぐお試しいただき、AWS re:Post for Amazon Bedrock まで、または通常の AWS サポートの連絡先を通じて、フィードバックをお寄せください。

当社と Mistral AI のコラボレーションと、それが当社のお客様にとって何を意味するかについてお読みください。

– Veliswa

原文はこちらです。