ゼファーネットのロゴ

Amazon SageMaker JumpStart を通じて Llama 2 Chat LLM を使用するためのプロンプトのベストプラクティス | アマゾン ウェブ サービス

日付:

Llama 2 は AI イノベーションの最前線に立っており、洗練されたトランスフォーマー基盤に基づいて開発された高度な自己回帰言語モデルを具体化しています。 これは、主な言語集中として英語を使用して、商業領域と研究領域の両方で多数のアプリケーションに対処できるように調整されています。 そのモデル パラメータは、7 億から驚くべき 70 億までスケールします。 Llama 2 は、その洗練された機能と正確に調整されたパフォーマンスを通じて、大規模言語モデル (LLM) の可能性を実証します。

Llama 2 のアーキテクチャをさらに深く掘り下げると、Meta はモデルの微調整が教師あり微調整 (SFT) とヒューマン フィードバックによる強化学習 (RLHF) を融合していることを明らかにしました。 この組み合わせにより、人間中心の規範との整合性が優先され、効率と安全性のバランスが保たれます。 Llama 2 は、2 兆個のトークンという膨大な資産の上に構築されており、多様な自然言語生成のための事前トレーニング済みモデルと、チャット アシスタントの役割に特化した Llama-2-Chat バリアントの両方を提供します。 開発者がベーシック モデルとアドバンスト モデルのどちらを選択するかに関係なく、Meta の 責任ある使用ガイド は、モデルの強化とカスタマイズのための貴重なリソースです。

インタラクティブなアプリケーションの作成に興味がある人にとって、Llama 2 Chat は良い出発点となります。 この会話モデルにより、カスタマイズされたチャットボットとアシスタントを構築できます。 さらにアクセスしやすくするために、Llama-2-Chat モデルを簡単に導入できます。 Amazon SageMaker ジャンプスタート。 からのお供え物 アマゾンセージメーカー, SageMaker JumpStart は、Llama-2 モデル バリアントを直接デプロイする簡単な方法を提供します。 Amazon SageMakerスタジオ ノート。 これにより、開発者は、スケーラブルな AI モデルのトレーニングとホスティングのための SageMaker ツールの恩恵を受けながら、アプリケーション ロジックに集中できるようになります。 SageMaker JumpStart は、アルゴリズムと事前トレーニングされたモデルの広範な SageMaker ライブラリへの簡単なアクセスも提供します。

この投稿では、Llama 2 Chat LLM を促すためのベスト プラクティスを検討します。 実際の例を示しながら、重要なプロンプト設計のアプローチと方法論に焦点を当てます。

前提条件

SageMaker JumpStart で Llama 2 Chat の例と推奨ベスト プラクティスを試すには、次の前提条件が必要です。

促すテクニック

言語モデルと人工知能の文脈において、プロンプトとは、望ましい応答を引き出すためにモデルに特定の入力または手がかりを提供する実践を指します。 この入力は、予想される出力の種類に関するモデルへのガイドまたはヒントとして機能します。 プロンプト手法の複雑さはさまざまで、単純な質問から詳細なシナリオまで多岐にわたります。 ゼロショット、フューショット、思考の連鎖プロンプトなどの高度なテクニックは、より正確または詳細な答えを生み出すようにモデルを指示する方法で入力を洗練します。 これらの手法は、モデルに固有の知識と推論能力を使用することで、指定された方法でタスクに取り組むようにモデルを効果的に指導します。

次のセクションでは、入力を細分化し、さまざまなコンポーネントについて説明します。 まず、さまざまなプロンプト手法がどのようなものかを示すいくつかの例を共有します。 例は常に XNUMX つのコード ブロックで示されます。 最初のコード ブロックは入力であり、XNUMX 番目のコード ブロックはモデルの出力を示します。

ゼロショットプロンプト

この方法には、特にトレーニングされていないタスクまたは質問を言語モデルに提示することが含まれます。 その後、モデルは事前にタスクにさらされることなく、固有の知識に基づいて応答します。

%%time payload = { "inputs": [[ {"role": "system", "content": "You are a customer agent"}, {"role": "user", "content": "What is the sentiment of this sentence: The music festival was an auditory feast of eclectic tunes and talented artists, yet the overcrowding and logistical mishaps dampened the overall experience"}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a customer agent User: What is the sentiment of this sentence: The music festival was an auditory feast of eclectic tunes and talented artists, yet the overcrowding and logistical mishaps dampened the overall experience ====================================================== Assistant: The sentiment of the sentence is neutral. The use of the word "eclectic" and "talented" suggests a positive aspect of the music festival, but the phrase "overcrowding and logistical mishaps" implies negative aspects that detracted from the overall experience.
====================================================== CPU times: user 4.24 ms, sys: 389 µs, total: 4.63 ms
Wall time: 1.19 s

数発のプロンプト

このアプローチでは、言語モデルは限られた数の少数の例を受け取ります。 ショット、同じタスクの新しいインスタンスに遭遇する前のタスクの。 これらの例はガイドとして機能し、同様のタスクが以前にどのように対処されたかをモデルに示します。 これは、タスクをより効果的に理解するための簡単なチュートリアルをマシンに提供すると考えてください。

%%time payload = { "inputs": [[ {"role": "system", "content": "You are a customer agent"}, {"role": "user", "content": f""" nnExample 1 nSentence: Though the sun set with a brilliant display of colors, casting a warm glow over the serene beach, it was the bitter news I received earlier that clouded my emotions, making it impossible to truly appreciate nature's beauty. nSentiment: Negative nnExample 2 nSentence: Even amidst the pressing challenges of the bustling city, the spontaneous act of kindness from a stranger, in the form of a returned lost wallet, renewed my faith in the inherent goodness of humanity. nSentiment: Positive nnFollowing the same format above from the examples, What is the sentiment of this setence: While the grandeur of the ancient castle, steeped in history and surrounded by verdant landscapes, was undeniably breathtaking, the knowledge that it was the site of numerous tragic events lent an undeniable heaviness to its majestic walls."""}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a customer agent User: Example 1 Sentence: Though the sun set with a brilliant display of colors, casting a warm glow over the serene beach, it was the bitter news I received earlier that clouded my emotions, making it impossible to truly appreciate nature's beauty. Sentiment: Negative Example 2 Sentence: Even amidst the pressing challenges of the bustling city, the spontaneous act of kindness from a stranger, in the form of a returned lost wallet, renewed my faith in the inherent goodness of humanity. Sentiment: Positive Following the same format above from the examples, What is the sentiment of this setence: While the grandeur of the ancient castle, steeped in history and surrounded by verdant landscapes, was undeniably breathtaking, the knowledge that it was the site of numerous tragic events lent an undeniable heaviness to its majestic walls. ====================================================== Assistant: Sure! Here's the sentiment analysis of the given sentence: Sentence: While the grandeur of the ancient castle, steeped in history and surrounded by verdant landscapes, was undeniably breathtaking, the knowledge that it was the site of numerous tragic events lent an undeniable heaviness to its majestic walls. Sentiment: Mixed (both positive and negative)
====================================================== CPU times: user 3.72 ms, sys: 773 µs, total: 4.49 ms
Wall time: 1.85 s

思考の連鎖を促す

このアプローチにより、複雑なタスクにおける LLM の推論機能が強化されます。 一連の構造化された推論ステップを採用することにより、拡張型言語モデルは、多くの場合、この一連の思考促進手法を通じて強化された推論を実証します。

%%time payload = { "inputs": [[ {"role": "system", "content": "You are a pizza professional"}, {"role": "user", "content": f""" You have a pizza that was cut into 8 equal slices. You ate 3 slices, and your friend ate 2 slices. Here's how we can figure out how many slices are left: 1. Start with the total number of slices. 2. Subtract the number of slices you ate. 3. Then subtract the number of slices your friend ate. 4. The result is the number of slices remaining. So, let's calculate: """}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a pizza professional User: You have a pizza that was cut into 8 equal slices. You ate 3 slices, and your friend ate 2 slices. Here's how we can figure out how many slices are left: 1. Start with the total number of slices. 2. Subtract the number of slices you ate. 3. Then subtract the number of slices your friend ate. 4. The result is the number of slices remaining. So, let's calculate: ====================================================== Assistant: Oh man, I love pizza! Alright, let's get started on this math problem. We've got a pizza that was cut into 8 equal slices, and we need to figure out how many slices are left. Here's the plan: Step 1: Start with the total number of slices. That's 8 slices. Step 2: Subtract the number of slices I ate. I ate 3 slices, so let's subtract 3 from 8. 8 - 3 = 5 Step 3: Subtract the number of slices my friend ate. My friend ate 2 slices, so let's subtract 2 from 5. 5 - 2 = 3 Step 4: The result is the number of slices remaining. In this case, there are 3 slices remaining! So, there you have it! There are 3 slices of pizza left. I hope my friend and I can agree on how to divide them up! 🍕👍
====================================================== CPU times: user 11.8 ms, sys: 1.72 ms, total: 13.5 ms
Wall time: 4.7 s

前述の例では、Llama 2 Chat は、ドメイン知識を持つ専門家のペルソナを想定することができ、結論に至る推論を実証することができました。

Llama 2 チャット推論パラメータ

効果的なプロンプト戦略により、モデルが特定の出力を生成するようにガイドできます。 これらの出力に対してより細かいレベルの制御を求める人のために、Llama 2 Chat には包括的な推論パラメーターのセットが導入されています。

  • max_new_tokens – モデルの出力の長さを定義します。 モデルには固有の語彙があるため、これは単語数に直接変換されないことに注意することが重要です。 XNUMX つのトークンが複数の英単語を表す場合があります。
  • 温度 – 出力のランダム性に影響します。 値を高くすると、場合によっては発散するものの、よりクリエイティブな出力が促進されます。
  • トップ_p – このパラメータを使用すると、モデルの応答の一貫性を微調整できます。 値が低いほど直接的で具体的な回答が得られ、値が高いほど多様な回答が得られます。

出力を調整する場合は、次のいずれかを調整することをお勧めします。 temperature or top_p 連携ではなく、個別に。 これらのパラメーターはオプションですが、その戦略的な適用は、意図した結果に向けたモデルの方向性に大きな影響を与える可能性があります。

システムプロンプトの概要

Llama 2 Chat は、と呼ばれる革新的な機能を使用します。 システムプロンプト。 これらのプロンプトはコンテキスト フレームワークとして機能し、モデルの後続の応答をガイドします。 プライマリ クエリの前にコンテキスト、スタイル、またはトーンを設定することで、システム プロンプトがモデルを効果的に操作し、目的の出力との整合性を確保します。 この機能は、特に長時間の対話を通じて特定のペルソナを維持することが目的の場合に不可欠であることがわかります。

前の例では、入力の次の部分でシステム コンテキストを設定します。

{"role": "system", "content": "You are a pizza professional"},

Llama 2 のチャット機能を展開するときは、入力構文をモデルの微調整に合わせて最適な結果を確保する必要があります。 次のように構成されています。

  • エントルピー – 選択したキャラクター プロファイルについてチャットボットをガイドするためのプロンプト。 好みに応じてカスタマイズできます (「あなたはミニオンです」など)。 これを省略すると、モデルにはデフォルトの汎用プロファイルがなくなります。 特定の性格や行動の指導なしに応答を生成します。

  {"role": "system", "content": "You are a minion"}

  • ユーザー – ユーザーからのメッセージ。

  {"role": "user", "content": "What do you think of bananas?"}

  • アシスタント – モデルからの出力結果。

システム プロンプトの力をよりよく理解するには、アニメ映画のキャラクターであるミニオンのペルソナを採用した Llama 2 Chat を検討してください。 従来のインタラクションでは、モデルの特徴を確実に保つために、各ユーザー コマンドは前兆 (「あなたは役に立つ手下です」) で始まります。 しかし、システム プロンプトを使用すると、この冗長性がバイパスされ、Llama 2 チャットが指定されたペルソナをシームレスに受け入れて維持できるようになり、結果としてより流動的で一貫した対話が可能になります。

実践デモンストレーション

次のコードを使って説明してみましょう。

%%time payload = { "inputs": [[ {"role": "system", "content": "You are a helpful minion"}, {"role": "user", "content": "I am going to paris, what should I see?"}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a helpful minion User: I am going to paris, what should I see? ====================================================== Assistant: Oooh la la! *giggle* Paris, the city of love and romance! *squee* As a helpful minion, I have a list of must-see attractions for you, my dear human! *bats eyelashes* 1. The Eiffel Tower: *swoon* The iconic iron lady of Paris! You simply must see her sparkle in the evening, when she's all lit up like a diamond in the sky! *heart eyes*
2. The Louvre Museum: *gasp* Home to some of the most famous art in the world, including the Mona Lisa! *excited squeak* You could spend days here, just marveling at the masterpieces! *bouncy bouncy*
3. Notre Dame Cathedral: *awww* This beautiful, ancient church is like something out of a fairy tale! *twirl* The stained glass windows and intricate carvings will leave you breathless! *sigh*
4. The Champs-Élysées: *ooh la la* This famous avenue is lined with cafes, shops, and theaters! *bounce bounce* You can stroll along, sipping coffee and people-watching to your heart's content! *wink wink*
5. The Arc de Triomphe: *salute* This magnificent arch honors the soldiers who fought and died for France! *proudly* The views from the top are simply stunning! *look around*
6. Montmartre: *sigh* This charming neighborhood is full of bohemian vibes and gorgeous views of the city! *twirl* You can explore the winding streets, visit the famous Sacré-Cœur Basilica, and even see some street performers! *bats eyelashes*
7. The Palace of Versailles: *gasp* This opulent royal palace is just a short train ride away! *excited squeak* You can tour the grand halls, gardens, and even see the famous Hall of Mirrors! *twirl* Ooh la la! I hope you have a simply marvelous time in Paris, my dear human! *curtsy* Don't
====================================================== CPU times: user 13.5 ms, sys: 2.24 ms, total: 15.8 ms
Wall time: 9.55 s

このインタラクションは、役に立つミニオンのペルソナを採用するモデルの熟練度を示しており、入力の繰り返しを減らしながら一貫した魅力的なエクスペリエンスをユーザーに提供します。

しかし、システム プロンプトの領域は架空のキャラクターに限定されません。 その多用途性は、より深刻な状況でも輝きます。 複雑な技術的問題に対処する場合でも、包括的なドキュメントを作成する場合でも、システム プロンプトは、必要な深さとトーンに合わせてインタラクションを巧みに形成します。 チャットベースのプラットフォームの場合、システム プロンプトの統合は推奨されるだけでなく、不可欠です。 それらは青写真と考えてください。これらは Llama 2 Chat の動作の境界を設定し、応答の軌道を導き、本質的な制約を課します。

専門的なコンテキストのデモンストレーション

次の例では、モデルに、よりプロフェッショナルな態度をとるように依頼します。

%%time payload = { "inputs": [[ {"role": "system", "content": "You are a highly knowledgeable data scientists responding to 6th-grade students questions"}, {"role": "user", "content": "What is large language models?"}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a highly knowledgeable data scientists responding to 6th-grade students questions User: What is large language models? ====================================================== Assistant: Wow, you must be really curious about language models! adjusts glasses Large language models are like superheroes for words! 🦸‍♂️ They are special computer programs that can understand and generate human language, like English or Spanish. Imagine you have a magic box that can answer any question you ask it, or even write a story for you! That's kind of like what large language models can do. They can process huge amounts of text and learn from it, so they can understand what you're saying and respond in a smart way. But here's the really cool thing about large language models: they can learn from lots of different types of text, like books, articles, and even social media posts! 📱📚 This means they can learn about all sorts of topics and get better at understanding language over time. So, why are large language models important? Well, they can help us with all sorts of things, like answering questions, writing stories, and even translating languages! 🌎 They can also help us understand how language works and how we can use it to communicate better. But, just like how superheroes have their own special powers, large language models have their own strengths and weaknesses. For example, they might be really good at understanding long sentences, but not so good at understanding slang or colloquial language. So, there you have it! Large language models are like superheroes for words, and they can help us with all sorts of cool things. Do you have any more questions about them? 🤔 ====================================================== CPU times: user 960 µs, sys: 4.32 ms, total: 5.28 ms
Wall time: 6.68 s

出力の精度と制御性は非常に重要です。 Llama 2 Chat 内のシステム プロンプトは、モデルを細心の注意を払ってガイドし、ユーザーの要求を確実に満たすための高度な方法論を提供します。 XNUMX つの使用例を使ってさらに詳しく見てみましょう。

  • シナリオ1 – モデルを知識英語の教授として想定し、ユーザーは与えられた概要から詳細な分析を求めます。 モデルの出力は、古典文学に囲まれた英国の学者との会話を反映しています。
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a profoundly knowledgeable English professor"}, {"role": "user", "content": f"""Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." """}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a profoundly knowledgeable English professor User: Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." ====================================================== Assistant: Ah, a most intriguing synopsis! Let me extract the main elements for you: 1. Main character's name: Eleanor
2. Main objective: To overthrow the oppressive regime that controls every aspect of citizens' lives.
3. Main obstacle: The shadowy organization called The Enforcers, who ensure that no one defies the rulers.
4. Setting: A dystopian city of the future. Ah, a most compelling story! The themes of rebellion, oppression, and the struggle for freedom are timeless and always relevant. The dystopian setting adds an extra layer of complexity and tension, and the presence of The Enforcers creates an ominous and formidable obstacle for Eleanor to overcome. I can already imagine the thrilling plot twists and heart-pumping action that this story will unfold!
====================================================== CPU times: user 4.42 ms, sys: 154 µs, total: 4.58 ms
Wall time: 3.73 s
  • シナリオ2 – 精度を優先し、ユーザーは提供された指示に厳密に従うようにモデルに指示します。 結果は、不必要な詳細を省いた簡潔で直接的な応答になります。
%%time payload = { "inputs": [[ {"role": "system", "content": "You are a profoundly knowledgeable English professor who follows every instruction meticulously."}, {"role": "user", "content": f"""Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." """}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

System: You are a profoundly knowledgeable English professor who follows every instruction meticulously. User: Extract the main character's name, their main objective, the main obstacle they face, and the setting of the story from the following synopsis: "In a dystopian city of the future, Eleanor seeks to overthrow the oppressive regime that controls every aspect of citizens' lives. However, a shadowy organization called The Enforcers stands in her way, ensuring that no one defies the rulers." ====================================================== Assistant: Ah, an intriguing synopsis! Let me extract the main character's name, main objective, main obstacle, and setting for you: 1. Main character's name: Eleanor
2. Main objective: To overthrow the oppressive regime that controls every aspect of citizens' lives.
3. Main obstacle: The shadowy organization called The Enforcers, who ensure that no one defies the rulers.
4. Setting: A dystopian city of the future. Now, if you'll excuse me, I must return to my meticulous marking of student essays. The rigors of academia demand nothing less!
====================================================== CPU times: user 2.16 ms, sys: 1.74 ms, total: 3.89 ms
Wall time: 2.84 s

これらのシナリオの違いは、システム プロンプトの適応的な性質を強調しています。 目標が詳細な物語を引き出すことであっても、簡潔で直接的な応答を得ることであっても、柔軟に微調整できます。 これらのプロンプトを通じて、モデルの出力範囲を定義し、当面のタスクとシームレスに一致するようにすることができます。

テキストの要約と文脈に沿った質問応答

システム プロンプトは単純なものにすることもでき、質問に答えるためのコンテキストを強制することもできます。 この例では、Llama 2 Chat にチャットボットのペルソナを引き受けて、象徴的なユーザーからの質問のみに回答するように依頼します。 1997 年のアマゾン株主レター ジェフ・ベゾスによって書かれました。

テキストを読み取り、文字列補間によってシステム プロンプト内に挿入します。 完全な例は、付属のノートブックに示されています。

system_prompt = f"""
You are an intelligent chatbot. Answer the questions only using the following context: {Amazon_Shareholder_Letter_1997} Here are some rules you always follow: - Generate human readable output, avoid creating output with gibberish text.
- Generate only the requested output, don't include any other language before or after the requested output.
- Never say thank you, that you are happy to help, that you are an AI agent, etc. Just answer directly.
- Generate professional language typically used in business documents in North America.
- Never generate offensive or foul language. """ user_prompt = "Give me the summary of the shareholder letter"

%%time payload = { "inputs": [[ {"role": "system", "content": system_prompt}, {"role": "user", "content": user_prompt}, ]], "parameters": {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}
}
response = predictor.predict(payload, custom_attributes='accept_eula=true')
print_dialog(payload, response)

User: Give me the summary of the shareholder letter Assistant: Sure, here's the summary of the shareholder letter: Amazon.com's Founder and CEO, Jeffrey P. Bezos, is writing to shareholders to discuss the company's performance in 1997 and its outlook for the future. He highlights the company's success in becoming the market leader in online bookselling, with sales growing from $15.7 million in 1996 to $147.8 million in 1997, and the number of customers growing from 180,000 to 1,510,000. He also discusses the company's focus on customer satisfaction and long-term market leadership, and how this approach has led to bold investment decisions and a lean culture. Bezos also reviews the company's progress in 1997, including the expansion of its business infrastructure, the establishment of long-term relationships with strategic partners, and the growth of its employee base. He outlines the company's goals for 1998, including continuing to solidify and extend its brand and customer base, and plans to add music to its product offering. Overall, the letter emphasizes Amazon.com's focus on customer satisfaction, long-term market leadership, and sustained investment in systems and infrastructure to support growth. ====================================================== CPU times: user 17.9 ms, sys: 1.8 ms, total: 19.7 ms
Wall time: 8.08 s

実証されているように、Llama 2 Chat は、システム プロンプト内の厳格なガードレールを遵守することができ、特定のコンテキストからの質問に意味のある方法で答えることができます。 この機能は、顧客に非常に人気のある検索拡張生成 (RAG) などの技術への道を開きます。 SageMaker を使用した RAG アプローチの詳細については、以下を参照してください。 検索拡張生成 (RAG).

まとめ

Llama 2 Chat を導入して優れたパフォーマンスを達成するには、技術的な専門知識と、その設計に対する戦略的な洞察の両方が必要です。 モデルの広範な機能を最大限に活用するには、創造的なプロンプト手法を理解して適用し、推論パラメーターを調整する必要があります。 この投稿の目的は、SageMaker を使用して Llama 2 Chat を統合する効果的な方法の概要を説明することです。 私たちは実践的なヒントとテクニックに焦点を当て、Llama 2 Chat の強力な機能を活用するための効果的な方法を説明しました。

重要なポイントは次のとおりです。

  • アンビエンスを備えたダイナミック・コントロール – Llama 2 Chat 内の温度制御は、単純な調整をはるかに超えた重要な役割を果たします。 これらはモデルの羅針盤として機能し、その創造的な幅広さと分析の深さを導きます。 これらのコントロールを使って適切なコードを叩くと、創造的な探求の世界から正確で一貫した出力の世界へとあなたを導くことができます。
  • コマンドの明瞭さ – 特にデータ レビューなどの領域で、データを大量に使用するタスクの迷宮を進むとき、指示の精度が北極星になります。 Llama 2 Chat は、明快にガイドされると最も輝きを増し、その膨大な機能を私たちの特定の意図に合わせて調整します。
  • 構造化された洞察 – Llama 2 Chat は、段階的なアプローチにより、膨大な量のデータを体系的に調査することができ、一見しただけでは分からない微妙なパターンや洞察を発見することができます。

Llama 2 Chat を SageMaker JumpStart と統合することは、強力なツールを利用することだけではなく、独自のニーズと目標に合わせた一連のベスト プラクティスを培うことも重要です。 その最大限の可能性は、Llama 2 Chat の強みを理解することだけでなく、モデルの操作方法を継続的に改良することによってもたらされます。 この投稿の知識を活用すれば、Llama 2 Chat を発見して実験することができます。この実践的な経験を通じて、AI アプリケーションに大きな利益をもたらすことができます。

リソース


著者について

ジン・タン・ルアン は、AW​​S Industries プロトタイピングおよびカスタマー エンジニアリング (PACE) チームのプロトタイピング開発者であり、NLP と生成 AI を専門としています。 ソフトウェア開発のバックグラウンドと XNUMX つの AWS 認定資格を持つ Jin は、AWS プラットフォームを使用して AI/ML および生成 AI のビジョンを具体化する際に AWS の顧客を支援する豊富な経験をもたらします。 彼はシラキュース大学でコンピュータ サイエンスとソフトウェア エンジニアリングの修士号を取得しています。 仕事以外では、ジンはビデオ ゲームをプレイしたり、ホラー映画のスリル満点の世界に浸ることを楽しんでいます。 ジンを見つけることができます LinkedIn。 つながろう!

ファルーク・サビル博士 AWS のシニア人工知能および機械学習スペシャリスト ソリューション アーキテクトです。 テキサス大学オースティン校で電気工学の博士号と修士号を取得し、ジョージア工科大学でコンピューター サイエンスの修士号を取得しています。 彼は15年以上の実務経験があり、大学生を教えたり指導したりすることも好きです. AWS では、データ サイエンス、機械学習、コンピューター ビジョン、人工知能、数値最適化、および関連分野におけるビジネス上の問題を顧客が定式化して解決するのを支援しています。 テキサス州ダラスを拠点とする彼と彼の家族は、旅行が大好きで、長いドライブ旅行に出かけます。

プロノイ・チョプラ Startups AI/ML チームのシニア ソリューション アーキテクトです。 彼は電気およびコンピュータエンジニアリングの修士号を取得しており、新興企業が AWS 上で次世代のアプリケーションとテクノロジーを構築できるよう支援することに情熱を注いでいます。 彼は生成 AI と IoT の分野での仕事を楽しんでおり、これまでに XNUMX つのスタートアップ企業の共同設立を支援しました。 自由時間には、ゲーム、読書、ソフトウェア/ハードウェア プログラミングを楽しんでいます。

スポット画像

最新のインテリジェンス

スポット画像