[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

LLM推論基盤プロビジョニング講座 第3回 使用モデルの推論時消費メモリ見積もり

LLM推論基盤プロビジョニング講座 第3回 使用モデルの推論時消費メモリ見積もり

こんにちは!前回はLLMサービスへのリクエスト数見積もりについて解説しました。今回は7ステッププロセスの3番目、「使用モデルの推論時消費メモリ見積もり」について詳しく掘り下げていきます。 GPUメモリがリクエスト処理能力を決定する LLMサービス構築において、GPUが同時に処理できるリクエスト数はGPUメモリの消費量によって制約されます。 つまり、利用可能なGPUメモリがどれだけあるかによって、同時に何件のリクエストを処理できるかがほぼ決まります。 では、その具体例として、Llama3 8B(80億パラメータ)モデルをNVIDIA RTX A5000(24GB)にロードするケースを考えてみましょう。 このGPUには24GBのGPUメモリがありますが、すべてをリクエスト処理に使えるわけではありません。最初にモデル自体が一定量のメモリを消費し、残りの領域で実際のリクエスト処理を行います。 GPUメモリ消費の二大要素 GPUの消費メモリ量は主に以下の2つの要素によって決まります 1. モデルのフットプリント LLMをGPUに読み込んだときに最初に消費されるメモリ

By Qualiteg コンサルティング
システムとcondaのC++標準ライブラリ(libstdc++)のバージョン違い問題による事象と対処法解説

システムとcondaのC++標準ライブラリ(libstdc++)のバージョン違い問題による事象と対処法解説

こんにちは! 先日、dlibをつかったPythonアプリケーション(conda環境で動作する)作っていたところ、以下のようなエラーに遭遇しました。 ImportError: /home/mlu/anaconda3/envs/example_env/bin/../lib/libstdc++.so.6: version `GLIBCXX_3.4.32' not found (required by /home/mlu/anaconda3/envs/example_env/lib/python3.10/site-packages/_dlib_pybind11.cpython-310-x86_64-linux-gnu.so) 「dlib_pybind11モジュールがGLIBCXX_3.4.32を要求してるけど、みつからない!」という感じのエラーですね。

By Qualiteg プロダクト開発部
LLM推論基盤プロビジョニング講座 第2回 LLMサービスのリクエスト数を見積もる

LLM推論基盤プロビジョニング講座 第2回 LLMサービスのリクエスト数を見積もる

こんにちは! 今回はLLM推論基盤プロビジョニング講座 第2回です! STEP2 LLMサービスへのリクエスト数見積もり それでは、早速、LLM推論基盤プロビジョニングの第2ステップである「リクエスト数見積もり」の重要性と方法を解説いたします。 LLMサービスを構築する際に必要となるGPUノード数を適切に見積もるためには、まずサービスに対して想定されるリクエスト数を正確に予測する必要があります。 リクエスト数見積もりの基本的な考え方 LLMサービスへの想定リクエスト数から必要なGPUノード数を算出するプロセスは、サービス設計において非常に重要です。過小評価すればサービス品質が低下し、過大評価すれば無駄なコストが発生します。このバランスを適切に取るための基礎となるのがリクエスト数の見積もりです。 想定リクエスト数の諸元 リクエスト数を見積もるための5つの重要な要素(諸元)をみてみましょう。 1. DAU(Daily Active Users): 1日あたりの実際にサービスを利用するユーザー数です。これはサービスの規模を示す最も基本的な指標となります。 2. 1日

By Qualiteg コンサルティング
Zoom会議で肩が踊る?自動フレーミング映像安定化とAIによる性能向上の可能性

Zoom会議で肩が踊る?自動フレーミング映像安定化とAIによる性能向上の可能性

こんにちは! 本日は、自動フレーミング映像の安定化に関するアルゴリズム・ノウハウを解説いたします 第1章 問題の背景と目的 バストアップ映像を撮影する際、特にオンラインミーティングやYouTubeなどのトーク映像では、人物がうなずく、首を振るなどの自然な動作をした際に「首まわりや肩がフレーム内で上下に移動してしまう」という現象がしばしば起こります。これは、多くの場合カメラや撮影ソフトウェアが人物の「目や顔を画面中央に保とう」とする自動フレーミング機能の働きに起因します。 撮影対象の人物が頭を下げた際に、映像のフレーム全体が相対的に上方向へシフトし、その結果、本来動いていないはずの肩の部分が映像内で持ち上がっているように見えてしまう現象です。 本稿では、この問題を撮影後の後処理(ポストプロセッシング)のみを用いて、高速、高い精度かつロバストに解決する手法をご紹介します。 前半では、従来のCV(コンピュータービジョン)の手法を使い高速に処理する方法をご紹介します。後半では、AIを使用してより安定性の高い性能を実現する方法について考察します。 第2章 古典手法による肩の上下

By Qualiteg 研究部