[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

Claude Opus 4.7 完全ガイド — 公式情報で読み解くモデル仕様とClaude Codeでの実践ノウハウ

Claude Opus 4.7 完全ガイド — 公式情報で読み解くモデル仕様とClaude Codeでの実践ノウハウ

こんにちは! Qualitegプロダクト開発部です! 2026年4月に、AnthropicからClaude Opus 4.7がリリースされました。 今回のアップデートは、単にベンチマークが上がったという話ではありません。命令の解釈の仕方、応答長、ツール呼び出しの頻度、subagentの起動方針まで、モデルの振る舞いそのものが変わっています。 それに伴い、4.6までに作り込んだプロンプトや設定の一部は、外したり再評価したりする必要があります。本記事では、そうした移行時の落とし穴と、4.7時代に合わせた運用作法を、できるだけ実践的にまとめました。 この記事では、まずOpus 4.7で何が変わったのかを確認し、そのうえでClaude Code CLI版とClaude Code Web版でどう使いこなすべきかを見ていきます。 (通常のclaude.aiチャットUIは対象外です。) なお、けっこう長めの記事になっているので、 頭から通読していただく必要はありません。 下の目次から、気になるところや今すぐ困っているところだけ拾い読みしていただいて大丈夫です。 たとえば「とりあえず4.

By Qualiteg プロダクト開発部
サブスクリプションビジネスの完全ガイド【第3回】サブスクリプションビジネスの成長設計

サブスクリプションビジネスの完全ガイド【第3回】サブスクリプションビジネスの成長設計

こんにちは、Qualitegコンサルティングです! サブスクリプションビジネスの完全ガイド 第3回 をお届けいたします! 今回は、 PLG・SLG、ユニットエコノミクス、データ改善の実務ポイントについて解説していきたいとおもいます! この記事でわかること  ・PLG・SLG・ランドアンドエクスパンドの違いと使い分け  ・NRR、LTV/CAC、ペイバック期間など主要指標の実務的な読み方  ・バーンレートとランウェイから資金繰りリスクを把握する方法  ・ファネル分析・コホート分析・A/Bテストによる改善の進め方  ・AIプロダクト特有の原価構造とユニットエコノミクスの注意点 サブスクビジネス完全攻略 シリーズ一覧 第1回 『アープがさぁ...』『チャーンがさぁ...』にもう困らない サブスクビジネス完全攻略 第1回~『アープがさぁ...』『チャーンがさぁ...』にもう困らない完全ガイドなぜサブスクリプションモデルが世界を変えているのか、でもAI台頭でSaaSは終わってしまうの? こんにちは! Qualitegコンサルティングです! 新規事業戦略コンサルタントとして日々

By Qualiteg コンサルティング
(株)Qualiteg、Startup JAPAN EXPO 2026 出展レポート

(株)Qualiteg、Startup JAPAN EXPO 2026 出展レポート

こんにちは! Qualitegビジ開マーケティング部です! 2026年4月15日(水)から16日(木)までの2日間、幕張メッセで開催された「Startup JAPAN EXPO 2026」(主催:Eight / Sansan株式会社)に、 株式会社Qualitegとして出展してまいりました! Startup JAPAN EXPO 2026 出展概要 項目内容会期2026年4月15日(水)〜16日(木) 各日10:00〜17:00会場幕張メッセ 展示ホール7・8ブース16-16主催Eight(Sansan株式会社) 今回の展示テーマは—— 「依頼は並列に、思考は止めず。」 主力プロダクト「Bestllam®」に新搭載されたAIエージェント機能と、AIセキュリティソリューション「LLM-Audit™」の実演デモを、2日間にわたってお届けしました。 ブース番号は 16-16。展示ホール7・8の一角に、今回も気合いを入れて陣を構えました💪 プレスリリース 株式会社Qualiteg、

By Qualiteg ビジネス開発本部 | マーケティング部