[ChatStream] Llama2 対応の ChatPrompt実装

[ChatStream] Llama2 対応の ChatPrompt実装

こんにちは! (株)Qualiteg プロダクト開発部 です!

本稿では、 ChatStream にLlama2 対応の ChatPrompt を同梱いたしましたのでご紹介いたします!

現在の ChatPrompt は以下とおりとなっております。旧バージョンのChatStreamをご利用の場合も、以下コードにて Llama2対応可能です。(もちろん最新バージョンのChatStreamには同梱済です)

from chatstream import AbstractChatPrompt
from chatstream.chat_prompt.role_type import RoleType

SYSTEM_PROMPT = """\
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\
"""


class ChatPromptMetaLlamaLlama2Chat(AbstractChatPrompt):
    """
    meta-llama/Llama-2-7b-chat

    Prompt Guide from
    https://huggingface.co/blog/llama2
    """

    def __init__(self):
        super().__init__()  # Call the initialization of the base class
        self.set_system(f"<s>[INST] <<SYS>>\n{SYSTEM_PROMPT}\n<</SYS>>\n\n")
        self.set_requester("")
        self.set_responder("")

    def get_stop_strs(self):
        if not self.chat_mode:
            return None
        return []

    def get_custom_skip_echo_len(self, skip_echo_len):
        # modify skip_echo_len when using llama2
        num_turn = self.get_turn()
        if num_turn >= 2:
            modified_skip_echo_len = skip_echo_len + 1 * self.get_turn()
            return modified_skip_echo_len
        return skip_echo_len

    def get_replacement_when_input(self):
        return None

    def get_replacement_when_output(self):  # replace when response_text gotten
        return None

    def create_prompt(self, opts={}):
        if self.chat_mode == False:
            return self.get_requester_last_msg()

        # Chat Mode == True の場合のプロンプトを構築する
        ret = self.system

        for chat_content in self.get_contents(opts):

            chat_content_role_type = chat_content.get_role_type()
            chat_content_message = chat_content.get_message()

            if chat_content_message:
                merged_message = ""
                if chat_content_role_type == RoleType.REQUESTER:
                    merged_message = f"{chat_content_message} [/INST] "
                elif chat_content_role_type == RoleType.RESPONDER:
                    merged_message = f"{chat_content_message} </s><s>[INST] "
                ret += merged_message
            else:
                pass

        return ret

    def build_initial_prompt(self, chat_prompt):
        # 初期プロンプトは実装しない
        pass


本実装については、1点だけトリッキーな実装を含んでいます。
というのも、ChatStreamはストリーミングチャットが基本ですので新たに生成された1トークン分を更新していくことでリアルタイムで流れるようなチャットを実現しています。そのため、出力が期待と1文字でもズレてしまうと、ストリーミング時に1文字かけたり、全体が1文字ずつズレてしまったりする現象が発生しやすいです。

Llama2の出力の場合、ターンごとに1文字ずつ出力に空白文字が発生する現象が確認されており、 なにがしかのSpecial Token や空トークン、またコード変換の影響を疑っていましたが根本原因の特定に至らず、現象をキャンセルするための実装を入れています。

現象としましては、

以下のプロンプトを入力プロンプトとしたとき、

<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

Do you know the movie titanic [/INST] Hello! Yes, I'm familiar with the movie Titanic. It's a classic film directed by James Cameron, released in 1997, and starring Leonardo DiCaprio and Kate Winslet. The movie is based on the true story of the RMS Titanic, a British passenger liner that sank in the North Atlantic Ocean in 1912 after colliding with an iceberg. The film follows the story of Jack Dawson (played by DiCaprio) and Rose DeWitt Bukater (played by Winslet), who come from </s><s>[INST] Who is the director [/INST] The director of the movie "Titanic" is James Cameron. </s><s>[INST] Who is starred [/INST] ]  The movie "Titanic" features a star-studded cast, including:
* Leonardo DiCaprio as Jack Dawson
* Kate Winslet as Rose DeWitt Bukater
* Billy Zane as Cal Hockley
* Kathy Bates as Molly Brown
* Frances Fisher as Ruth DeWitt Bukater
* Bernard Hill as Captain Edward John Smith
* Jonathan Hyde as J. Bruce Ismay
* Eric Braeden as John Jacob Astor IV
* Gloria Stuart as Old Rose

These actors brought the characters from the movie to life and </s><s>[INST] 

出力は以下のようになります

[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

Do you know the movie titanic [/INST] Hello! Yes, I'm familiar with the movie Titanic. It's a classic film directed by James Cameron, released in 1997, and starring Leonardo DiCaprio and Kate Winslet. The movie is based on the true story of the RMS Titanic, a British passenger liner that sank in the North Atlantic Ocean in 1912 after colliding with an iceberg. The film follows the story of Jack Dawson (played by DiCaprio) and Rose DeWitt Bukater (played by Winslet), who come from  [INST] Who is the director [/INST] The director of the movie "Titanic" is James Cameron.  [INST] Who is starred [/INST]

Input:
Do you know the movie titanic [/INST] Hello! Yes, I'm familiar with the movie Titanic. It's a classic film directed by James Cameron, released in 1997, and starring Leonardo DiCaprio and Kate Winslet. The movie is based on the true story of the RMS Titanic, a British passenger liner that sank in the North Atlantic Ocean in 1912 after colliding with an iceberg. The film follows the story of Jack Dawson (played by DiCaprio) and Rose DeWitt Bukater (played by Winslet), who come from [INST] Who is the director [/INST] The director of the movie "Titanic" is James Cameron. [INST] Who is starred [/INST] 

つまり入力プロンプトが [INST] つまり 半角スペース1つ[INST] でも出力で、 [INST]半角スペース2つ + [INST] となって戻ってくるため、新規生成文章の切り出しで1レスポンスにたいして1文字ズレの発生が観測されます。

それならばと、入力プロンプトを 半角スペース2つ[INST] で入力したが、その場合は出力生成文は 半角スペース3つ[INST]
となり、ズレが解消されないようです。

このとき、通常のテキスト処理で trim していく方法もありますが、当ChatPromptではなるべくもとの入力と出力を変形しないことをポリシーとして、

    def get_custom_skip_echo_len(self, skip_echo_len):
        # modify skip_echo_len when using llama2
        num_turn = self.get_turn()
        if num_turn >= 2:
            modified_skip_echo_len = skip_echo_len + 1 * self.get_turn()
            return modified_skip_echo_len
        return skip_echo_len

のように、 skip_echo_len をターンにあわせて調整することでピッタリの切り出しに対応しました。約1000通りの入出力において、問題なく切り出せているため、本手法を workaround として採用しています。ちょっとした見落としの可能性も高そうなので根治のために研究部側で引き続き原因調査しています。

Llama2 をベースモデルとして採用しているほかモデルも同様の現象が発生していますが、本手法にて解決できました。

Read more

大企業のAIセキュリティを支える基盤技術 - 今こそ理解するActive Directory 第1回 基本概念の理解

大企業のAIセキュリティを支える基盤技術 - 今こそ理解するActive Directory 第1回 基本概念の理解

こんにちは! 今回から数回にわたり Active Directory について解説してまいります。 Active Directory(AD:アクティブディレクトリー)は、Microsoft が開発したディレクトリサービスであり、今日の大企業における IT インフラストラクチャーにおいて、もはやデファクトスタンダードと言っても過言ではない存在となっており、組織内のユーザー、コンピューター、その他のリソースを一元的に管理するための基盤として広く採用されています。 AIセキュリティの現実:単独では機能しない ChatGPTやClaudeなどの生成AIが企業に急速に普及する中、「AIセキュリティ」という言葉が注目を集めています。情報漏洩の防止、不適切な利用の検知、コンプライアンスの確保など、企業が取り組むべき課題は山積みです。 しかし、ここで注意しなければいけない事実があります。それは、 AIセキュリティソリューションは、それ単体では企業環境で限定的な効果しか期待できない ということです。 企業が直面する本質的な課題 AIセキュリティツールを導入する際、企業のIT部門

By Qualiteg コンサルティング
自治体総合フェア2025に出展いたしました

自治体総合フェア2025に出展いたしました

こんにちは! 先週開催された自治体総合フェア2025に出展いたしましたので、写真で様子をふりかえりながら簡単にレポートいたします! 自治体総合フェア2025 開催概要 自治体総合フェアは公民連携の総合展示会で今年はは2025/7/16~18まで東京ビッグサイトにて開催されました。 株式会社 Qualiteg の出展内容 当社からは4名体制でAIアバター動画生成サービス「MotionVox™」をはじめ、LLMセキュリティソリューション「LLM-Audit™」、企業・自治体向けセキュアチャットサービス「Bestllam🄬」の展示をさせていただきました。 デモ内容 当日のご紹介内容の一部をご紹介いたします MotionVox™ MotionVox は、まるで、本物の人間のようなフォトリアリスティックなアバター動画を生成するサービスです。 これまでから機能を大幅拡張した MotionVox 2.0 をお披露目いたしました。 MotionVox 2.0では、以下のようなフィーチャーを追加いたしました! * まるで人間! リアリティをさらに向上したアバター *

By Qualiteg ビジネス開発本部 | マーケティング部
発話音声からリアルなリップシンクを生成する技術 第3回:wav2vec特徴量から口形パラメータへの学習

発話音声からリアルなリップシンクを生成する技術 第3回:wav2vec特徴量から口形パラメータへの学習

こんにちは! 前回までの記事では、 * wav2vecを用いた音声特徴量抽出の仕組み(第1回)と、 * リップシンク制作における累積ドリフトの補正技術(第2回) について解説してきました。今回はいよいよ、これらの技術を統合して実際に音声から口の動きを生成する核心部分に踏み込みます。 本記事で扱うのは、wav2vecが抽出した768次元の音響特徴量を、26個の口形制御パラメータの時系列データに変換する学習プロセスです。これは単なる次元削減ではありません。音の物理的特性を表す高次元ベクトルから、人間の口の動きという全く異なるモダリティへの変換なのです。この変換を実現するには、音韻と視覚的な口形の間にある複雑な対応関係を、ニューラルネットワークに学習させる必要があります。 特に重要なのは、この対応関係が静的ではなく動的であるという点です。同じ音素でも前後の文脈によって口の形が変わり、さらに音が聞こえる前から口が動き始めるという時間的なズレも存在します。これらの複雑な現象をどのようにモデル化し、学習させるのか。本記事では、LSTMとTransformerという2つの強力なアプロー

By Qualiteg 研究部
AI時代のデータ漏洩防止の要諦とテクノロジー:第1回 AI DLPとPROXY

AI時代のデータ漏洩防止の要諦とテクノロジー:第1回 AI DLPとPROXY

こんにちは!本日はAI時代のデータ漏洩防止について、とくにその通信技術面に焦点をあてつつ、AIセキュリティにどのように取り組んでいくべきか、解説いたします。 1. はじめに 生成AIの急速な普及により、企業のデータガバナンスは新たな局面を迎えています。ChatGPTやClaudeといった大規模言語モデル(LLM)は、業務効率を飛躍的に向上させる一方で、意図しない機密情報の漏洩という深刻なリスクをもたらしています。 従業員が何気なく入力した顧客情報や営業秘密が、AIサービスの学習データとして使用される可能性があることを、多くの組織はまだ十分に認識していません。従来のDLP(Data Loss Prevention)ソリューションは、メールやファイル転送を監視することには長けていましたが、リアルタイムで行われるWebベースのAIチャットやAIエージェントとの対話で発生しうる新しい脅威には対応できていないのが現状です。 本記事では、AI時代のデータ漏洩防止において中核となる技術、特にHTTPS通信のインターセプトとその限界について、技術的な観点から詳しく解説します。プロキシサーバー

By Qualiteg プロダクト開発部, Qualiteg コンサルティング