Upload 11 files

.gitattributes

@@ -19,6 +19,7 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,126 @@
+LLAMA 2 COMMUNITY LICENSE AGREEMENT	
+Llama 2 Version Release Date: July 18, 2023
+
+"Agreement" means the terms and conditions for use, reproduction, distribution and 
+modification of the Llama Materials set forth herein.
+
+"Documentation" means the specifications, manuals and documentation 
+accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
+libraries/llama-downloads/.
+
+"Licensee" or "you" means you, or your employer or any other person or entity (if 
+you are entering into this Agreement on such person or entity's behalf), of the age 
+required under applicable laws, rules or regulations to provide legal consent and that 
+has legal authority to bind your employer or such other person or entity if you are 
+entering in this Agreement on their behalf.
+
+"Llama 2" means the foundational large language models and software and 
+algorithms, including machine-learning model code, trained model weights, 
+inference-enabling code, training-enabling code, fine-tuning enabling code and other 
+elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
+libraries/llama-downloads/.
+
+"Llama Materials" means, collectively, Meta's proprietary Llama 2 and 
+Documentation (and any portion thereof) made available under this Agreement.
+
+"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you 
+are an entity, your principal place of business is in the EEA or Switzerland) and Meta 
+Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
+
+By clicking "I Accept" below or by using or distributing any portion or element of the 
+Llama Materials, you agree to be bound by this Agreement.
+
+1. License Rights and Redistribution. 
+
+      a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
+transferable and royalty-free limited license under Meta's intellectual property or 
+other rights owned by Meta embodied in the Llama Materials to use, reproduce, 
+distribute, copy, create derivative works of, and make modifications to the Llama 
+Materials.  
+      
+      b. Redistribution and Use.  
+
+            i. If you distribute or make the Llama Materials, or any derivative works 
+thereof, available to a third party, you shall provide a copy of this Agreement to such 
+third party. 
+            ii.  If you receive Llama Materials, or any derivative works thereof, from 
+a Licensee as part of an integrated end user product, then Section 2 of this 
+Agreement will not apply to you. 
+
+            iii. You must retain in all copies of the Llama Materials that you 
+distribute the following attribution notice within a "Notice" text file distributed as a 
+part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License, 
+Copyright (c) Meta Platforms, Inc. All Rights Reserved."
+
+            iv. Your use of the Llama Materials must comply with applicable laws 
+and regulations (including trade compliance laws and regulations) and adhere to the 
+Acceptable Use Policy for the Llama Materials (available at 
+https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into 
+this Agreement.
+
+            v. You will not use the Llama Materials or any output or results of the 
+Llama Materials to improve any other large language model (excluding Llama 2 or 
+derivative works thereof).  
+
+2. Additional Commercial Terms. If, on the Llama 2 version release date, the 
+monthly active users of the products or services made available by or for Licensee, 
+or Licensee's affiliates, is greater than 700 million monthly active users in the 
+preceding calendar month, you must request a license from Meta, which Meta may 
+grant to you in its sole discretion, and you are not authorized to exercise any of the 
+rights under this Agreement unless or until Meta otherwise expressly grants you 
+such rights.
+            
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE 
+LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE 
+PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, 
+EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY 
+WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR 
+FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE 
+FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING 
+THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR 
+USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE 
+LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, 
+NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS 
+AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, 
+CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
+IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF 
+ANY OF THE FOREGOING.
+ 
+5. Intellectual Property.
+
+      a. No trademark licenses are granted under this Agreement, and in 
+connection with the Llama Materials, neither Meta nor Licensee may use any name 
+or mark owned by or associated with the other or any of its affiliates, except as 
+required for reasonable and customary use in describing and redistributing the 
+Llama Materials.
+
+      b. Subject to Meta's ownership of Llama Materials and derivatives made by or 
+for Meta, with respect to any derivative works and modifications of the Llama 
+Materials that are made by you, as between you and Meta, you are and will be the 
+owner of such derivative works and modifications.
+
+      c. If you institute litigation or other proceedings against Meta or any entity 
+(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama 
+Materials or Llama 2 outputs or results, or any portion of any of the foregoing, 
+constitutes infringement of intellectual property or other rights owned or licensable 
+by you, then any licenses granted to you under this Agreement shall terminate as of 
+the date such litigation or claim is filed or instituted. You will indemnify and hold 
+harmless Meta from and against any claim by any third party arising out of or related 
+to your use or distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your 
+acceptance of this Agreement or access to the Llama Materials and will continue in 
+full force and effect until terminated in accordance with the terms and conditions 
+herein. Meta may terminate this Agreement if you are in breach of any term or 
+condition of this Agreement. Upon termination of this Agreement, you shall delete 
+and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the 
+termination of this Agreement. 
+
+7. Governing Law and Jurisdiction. This Agreement will be governed and 
+construed under the laws of the State of California without regard to choice of law 
+principles, and the UN Convention on Contracts for the International Sale of Goods 
+does not apply to this Agreement. The courts of California shall have exclusive 
+jurisdiction of any dispute arising out of this Agreement. 
+

README.md

@@ -1,13 +1,37 @@
 ---
-title: ELYZA Japanese Llama 2 13b Instruct Demo
-emoji: 📚
+title: ELYZA-japanese-Llama-2-13b-instruct-demo
+emoji: 🎓
 colorFrom: purple
-colorTo: indigo
+colorTo: gray
 sdk: gradio
-sdk_version: 4.12.0
+sdk_version: 3.41.0
 app_file: app.py
-pinned: false
-license: llama2
+pinned: true
+suggested_hardware: a100-large
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# ELYZA-japanese-Llama-2-13b-instruct-demo
+
+## 概要
+- [ELYZA-japanese-Llama-2-13b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b)は、[株式会社ELYZA](https://elyza.ai/) (以降「当社」と呼称) が[Llama2](https://ai.meta.com/llama/)をベースとして日本語能力を拡張するために事前学習を行ったモデルです。
+- [ELYZA-japanese-Llama-2-13b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-instruct)は ELYZA-japanese-Llama-2-13b を弊社独自のinstruction tuning用データセットで事後学習したモデルです。
+    - 本デモではこのモデルが使われています。
+- 詳細は[Blog記事](https://note.com/elyza/n/n5d42686b60b7)を参照してください。
+- 本デモではこちらの[Llama-2 7B Chat](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat)のデモをベースにさせていただきました。
+
+## License
+- Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
+
+## 免責事項
+- 当社は、本デモについて、ユーザーの特定の目的に適合すること、期待する機能・正確性・有用性を有すること、出力データが完全性、正確性、有用性を有すること、ユーザーによる本サービスの利用がユーザーに適用のある法令等に適合すること、継続的に利用できること、及び不具合が生じないことについて、明示又は黙示を問わず何ら保証するものではありません。
+- 当社は、本デモに関してユーザーが被った損害等につき、一切の責任を負わないものとし、ユーザーはあらかじめこれを承諾するものとします。
+- 当社は、本デモを通じて、ユーザー又は第三者の個人情報を取得することを想定しておらず、ユーザーは、本デモに、ユーザー又は第三者の氏名その他の特定の個人を識別することができる情報等を入力等してはならないものとします。
+- ユーザーは、当社が本デモ又は本デモに使用されているアルゴリズム等の改善・向上に使用することを許諾するものとします。
+
+## 本デモで入力・出力されたデータの記録・利用に関して
+- 本デモで入力・出力されたデータは当社にて記録させていただき、今後の本デモ又は本デモに使用されているアルゴリズム等の改善・向上に使用させていただく場合がございます。
+
+## We are hiring!
+- 当社 (株式会社ELYZA) に興味のある方、ぜひお話ししませんか？
+- 機械学習エンジニア・インターン募集: https://open.talentio.com/r/1/c/elyza/homes/2507
+- カジュアル面談はこちら: https://chillout.elyza.ai/elyza-japanese-llama2-13b

USE_POLICY.md

@@ -0,0 +1,50 @@
+# Llama 2 Acceptable Use Policy
+
+Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).
+
+## Prohibited Uses
+We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to: 
+
+1. Violate the law or others’ rights, including to:
+    1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 
+        1. Violence or terrorism 
+        2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+        3. Human trafficking, exploitation, and sexual violence
+        4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+        5. Sexual solicitation
+        6. Any other criminal activity
+    2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+    3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+    4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 
+    5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
+    6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials
+    7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 
+
+
+
+2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:
+    1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
+    2. Guns and illegal weapons (including weapon development)
+    3. Illegal drugs and regulated/controlled substances
+    4. Operation of critical infrastructure, transportation technologies, or heavy machinery
+    5. Self-harm or harm to others, including suicide, cutting, and eating disorders
+    6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+
+
+
+3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:
+    1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+    2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+    3. Generating, promoting, or further distributing spam
+    4. Impersonating another individual without consent, authorization, or legal right
+    5. Representing that the use of Llama 2 or outputs are human-generated
+    6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
+4. Fail to appropriately disclose to end users any known dangers of your AI system 
+
+Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+* Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
+* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
+* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [[email protected]](mailto:[email protected])
+

app.py

@@ -0,0 +1,552 @@
+from datetime import datetime, timezone, timedelta
+import os
+import time
+from typing import AsyncGenerator
+import uuid
+import asyncio
+import logging
+import textwrap
+
+import boto3
+from botocore.config import Config
+import gradio as gr
+import pandas as pd
+import torch
+
+from model_vllm import get_input_token_length, run
+
+logging.basicConfig(encoding='utf-8', level=logging.ERROR)
+logger = logging.getLogger(__name__)
+
+JST = timezone(timedelta(hours=+9), 'JST')
+
+DEFAULT_SYSTEM_PROMPT = 'あなたは誠実で優秀な日本人のアシスタントです。'
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 512
+MAX_INPUT_TOKEN_LENGTH = 4000
+
+TITLE = '# ELYZA-japanese-Llama-2-13b-instruct'
+DESCRIPTION = """
+## 概要
+- [ELYZA-japanese-Llama-2-13b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b)は、[株式会社ELYZA](https://elyza.ai/) (以降「当社」と呼称) が[Llama2](https://ai.meta.com/llama/)をベースとして日本語能力を拡張するために事前学習を行ったモデルです。
+- [ELYZA-japanese-Llama-2-13b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-instruct)は ELYZA-japanese-Llama-2-13b を弊社独自のinstruction tuning用データセットで事後学習したモデルです。
+    - 本デモではこのモデルが使われています。
+- 詳細は[Blog記事](https://note.com/elyza/n/n5d42686b60b7)を参照してください。
+- 本デモではこちらの[Llama-2 7B Chat](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat)のデモをベースにさせていただきました。
+
+## License
+- Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
+
+## 免責事項
+- 当社は、本デモについて、ユーザーの特定の目的に適合すること、期待する機能・正確性・有用性を有すること、出力データが完全性、正確性、有用性を有すること、ユーザーによる本サービスの利用がユーザーに適用のある法令等に適合すること、継続的に利用できること、及び不具合が生じないことについて、明示又は黙示を問わず何ら保証するものではありません。
+- 当社は、本デモに関してユーザーが被った損害等につき、一切の責任を負わないものとし、ユーザーはあらかじめこれを承諾するものとします。
+- 当社は、本デモを通じて、ユーザー又は第三者の個人情報を取得することを想定しておらず、ユーザーは、本デモに、ユーザー又は第三者の氏名その他の特定の個人を識別することができる情報等を入力等してはならないものとします。
+- ユーザーは、当社が本デモ又は本デモに使用されているアルゴリズム等の改善・向上に使用することを許諾するものとします。
+
+## 本デモで入力・出力されたデータの記録・利用に関して
+- 本デモで入力・出力されたデータは当社にて記録させていただき、今後の本デモ又は本デモに使用されているアルゴリズム等の改善・向上に使用させていただく場合がございます。
+
+## We are hiring!
+- 当社 (株式会社ELYZA) に興味のある方、ぜひお話ししませんか？
+- 機械学習エンジニア・インターン募集: https://open.talentio.com/r/1/c/elyza/homes/2507
+- カジュアル面談はこちら: https://chillout.elyza.ai/elyza-japanese-llama2-13b
+"""
+
+_format_example = lambda s: textwrap.dedent(s).strip()
+
+examples = list(map(_format_example, [
+    """
+        「キムチプリン」という新商品を考えています。この商品に対する世間の意見として想像されるものを箇条書きで3つ教えて
+    """,
+    """
+        「メタリック」から「気分上々」までが自然につながるように、あいだの単語を連想してください。
+    """,
+    """
+       自律神経や副交感神経が乱れている、とはどのような状態ですか？科学的に教えて 
+    """,
+    """
+        日本国内で観光に行きたいと思っています。東京、名古屋、大阪、京都、福岡の特徴を表にまとめてください。
+        列名は「都道府県」「おすすめスポット」「おすすめグルメ」にしてください。
+    """,
+    """
+        私の考えた創作料理について、想像して説明を書いてください。
+
+        1. トマトマット
+        2. 餃子風もやし炒め
+        3. おにぎりすぎ
+    """,
+]))
+
+if not torch.cuda.is_available():
+    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'
+
+try:
+    s3 = boto3.client(
+        's3',
+        aws_access_key_id=os.environ['AWS_ACCESS_KEY_ID'],
+        aws_secret_access_key=os.environ['AWS_SECRET_ACCESS_KEY'],
+        region_name=os.environ['S3_REGION'],
+        config=Config(
+            connect_timeout=5,
+            read_timeout=5,
+            retries={
+                'mode': 'standard',
+                'total_max_attempts': 3,
+            },
+        ),
+    )
+except Exception:
+    logger.exception('Failed to initialize S3 client')
+
+
+def clear_and_save_textbox(message: str) -> tuple[str, str]:
+    return '', message
+
+
+def display_input(message: str, history: list[tuple[str, str]]) -> list[tuple[str, str]]:
+    history.append((message, ''))
+    return history
+
+
+def delete_prev_fn(history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
+    try:
+        message, _ = history.pop()
+    except IndexError:
+        message = ''
+    return history, message or ''
+
+
+async def generate(
+    message: str,
+    history_with_input: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int,
+    temperature: float,
+    top_p: float,
+    top_k: int,
+    do_sample: bool,
+    repetition_penalty: float,
+) -> AsyncGenerator[list[tuple[str, str]], None]:
+    if max_new_tokens > MAX_MAX_NEW_TOKENS:
+        raise ValueError
+
+    history = history_with_input[:-1]
+    stream = await run(
+        message=message,
+        chat_history=history,
+        system_prompt=system_prompt,
+        max_new_tokens=max_new_tokens,
+        temperature=float(temperature),
+        top_p=float(top_p),
+        top_k=top_k,
+        do_sample=do_sample,
+        repetition_penalty=float(repetition_penalty),
+        stream=True,
+    )
+    async for response in stream:
+        yield history + [(message, response)]
+
+
+def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
+    response = asyncio.run(run(
+        message=message,
+        chat_history=[],
+        system_prompt=DEFAULT_SYSTEM_PROMPT,
+        max_new_tokens=DEFAULT_MAX_NEW_TOKENS,
+        temperature=1,
+        top_p=0.95,
+        top_k=50,
+        do_sample=False,
+        repetition_penalty=1.0,
+        stream=False
+    ))
+
+    return '', [(message, response)]
+
+def check_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> None:
+    input_token_length = get_input_token_length(message, chat_history, system_prompt)
+    if input_token_length > MAX_INPUT_TOKEN_LENGTH:
+        raise gr.Error(
+            f'合計対話長が長すぎます ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH})。入力文章を短くするか、「🗑️  これまでの出力を消す」ボタンを押してから再実行してください。'
+        )
+
+    if len(message) <= 0:
+        raise gr.Error('入力が空です。1文字以上の文字列を入力してください。')
+
+
+def convert_history_to_str(history: list[tuple[str, str]]) -> str:
+    res = []
+    for user_utt, sys_utt in history:
+        res.append(f'😃: {user_utt}')
+        res.append(f'🤖: {sys_utt}')
+    return '<br>'.join(res)
+
+
+def output_log(history: list[tuple[str, str]], uuid_list: list[tuple[str, str]]) -> None:
+    tree_uuid = uuid_list[0][0]
+    last_messages = history[-1]
+    last_uuids = uuid_list[-1]
+    parent_uuid = None
+    record_message = None
+    record_uuid = None
+    role = None
+    if last_uuids[1] == '':
+        role = 'user'
+        record_message = last_messages[0]
+        record_uuid = last_uuids[0]
+        if len(history) >= 2:
+            parent_uuid = uuid_list[-2][1]
+        else:
+            parent_uuid = last_uuids[0]
+    else:
+        role = 'assistant'
+        record_message = last_messages[1]
+        record_uuid = last_uuids[1]
+        parent_uuid = last_uuids[0]
+
+    now = datetime.fromtimestamp(time.time(), JST)
+    yyyymmdd = now.strftime('%Y%m%d')
+    created_at = now.strftime('%Y-%m-%d %H:%M:%S.%f')
+
+    d = {
+        'created_at': created_at,
+        'tree_uuid': tree_uuid,
+        'parent_uuid': parent_uuid,
+        'uuid': record_uuid,
+        'role': role,
+        'message': record_message,
+    }
+    try:
+        csv_buffer = pd.DataFrame(d, index=[0]).to_csv(index=None)
+        s3.put_object(
+            Bucket=os.environ['S3_BUCKET'],
+            Key=f"{os.environ['S3_KEY_PREFIX']}/{yyyymmdd}/{record_uuid}.csv",
+            Body=csv_buffer,
+        )
+    except Exception:
+        logger.exception('Failed to upload log to S3')
+    return
+
+
+def assign_uuid(history: list[tuple[str, str]], uuid_list: list[tuple[str, str]]) -> list[tuple[str, str]]:
+    len_history = len(history)
+    len_uuid_list = len(uuid_list)
+    new_uuid_list = [x for x in uuid_list]
+
+    if len_history > len_uuid_list:
+        for t_history in history[len_uuid_list:]:
+            if t_history[1] == '':
+                # 入力だけされてるタイミング
+                new_uuid_list.append((str(uuid.uuid4()), ''))
+            else:
+                # undoなどを経て、入力だけされてるタイミングを飛び越えた場合
+                new_uuid_list.append((str(uuid.uuid4()), str(uuid.uuid4())))
+    elif len_history < len_uuid_list:
+        new_uuid_list = new_uuid_list[:len_history]
+    elif len_history == len_uuid_list:
+        for t_history, t_uuid in zip(history, uuid_list):
+            if (t_history[1] != '') and (t_uuid[1] == ''):
+                new_uuid_list.pop()
+                new_uuid_list.append((t_uuid[0], str(uuid.uuid4())))
+            elif (t_history[1] == '') and (t_uuid[1] != ''):
+                new_uuid_list.pop()
+                new_uuid_list.append((t_uuid[0], ''))
+    return new_uuid_list
+
+
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(TITLE)
+
+    with gr.Row():
+        gr.HTML(
+            """
+        <div id="logo">
+            <img src='file/key_visual.png' width=1200 min-width=300></img>
+        </div>
+        """
+        )
+
+    with gr.Group():
+        chatbot = gr.Chatbot(
+            label='Chatbot',
+            height=600,
+            avatar_images=['person_face.png', 'llama_face.png'],
+        )
+        with gr.Column():
+            textbox = gr.Textbox(
+                container=False,
+                show_label=False,
+                placeholder='指示を入力してください。例: カレーとハンバーグを組み合わせた美味しい料理を3つ教えて',
+                scale=10,
+                lines=10,
+            )
+            submit_button = gr.Button(
+                '以下の説明文・免責事項・データ利用に同意して送信', variant='primary', scale=1, min_width=0
+            )
+            gr.Markdown(
+                '※ 繰り返しが発生する場合は、以下「詳細設定」の `repetition_penalty` を1.05〜1.20など調整すると上手くいく場合があります'
+            )
+    with gr.Row():
+        retry_button = gr.Button('🔄  同じ入力でもう一度生成', variant='secondary')
+        undo_button = gr.Button('↩️ ひとつ前の状態に戻る', variant='secondary')
+        clear_button = gr.Button('🗑️  これまでの出力を消す', variant='secondary')
+
+    saved_input = gr.State()
+    uuid_list = gr.State([])
+
+    with gr.Accordion(label='上の対話履歴をスクリーンショット用に整形', open=False):
+        output_textbox = gr.Markdown()
+
+    with gr.Accordion(label='詳細設定', open=False):
+        system_prompt = gr.Textbox(label='システムプロンプト', value=DEFAULT_SYSTEM_PROMPT, lines=8)
+        max_new_tokens = gr.Slider(
+            label='最大出力トークン数',
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        )
+        repetition_penalty = gr.Slider(
+            label='Repetition penalty',
+            minimum=1.0,
+            maximum=10.0,
+            step=0.1,
+            value=1.0,
+        )
+        do_sample = gr.Checkbox(label='do_sample', value=False)
+        temperature = gr.Slider(
+            label='Temperature',
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=1.0,
+        )
+        top_p = gr.Slider(
+            label='Top-p (nucleus sampling)',
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.95,
+        )
+        top_k = gr.Slider(
+            label='Top-k',
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        )
+
+    gr.Examples(
+        examples=examples,
+        inputs=textbox,
+        outputs=[textbox, chatbot],
+        fn=process_example,
+        cache_examples=True,
+    )
+
+    gr.Markdown(DESCRIPTION)
+
+    textbox.submit(
+        fn=clear_and_save_textbox,
+        inputs=textbox,
+        outputs=[textbox, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=check_input_token_length,
+        inputs=[saved_input, chatbot, system_prompt],
+        api_name=False,
+        queue=False,
+    ).success(
+        fn=display_input,
+        inputs=[saved_input, chatbot],
+        outputs=chatbot,
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=assign_uuid,
+        inputs=[chatbot, uuid_list],
+        outputs=uuid_list,
+    ).then(
+        fn=output_log,
+        inputs=[chatbot, uuid_list],
+    ).then(
+        fn=generate,
+        inputs=[
+            saved_input,
+            chatbot,
+            system_prompt,
+            max_new_tokens,
+            temperature,
+            top_p,
+            top_k,
+            do_sample,
+            repetition_penalty,
+        ],
+        outputs=chatbot,
+        api_name=False,
+    ).then(
+        fn=assign_uuid,
+        inputs=[chatbot, uuid_list],
+        outputs=uuid_list,
+    ).then(
+        fn=output_log,
+        inputs=[chatbot, uuid_list],
+    ).then(
+        fn=convert_history_to_str,
+        inputs=chatbot,
+        outputs=output_textbox,
+    )
+
+    button_event_preprocess = (
+        submit_button.click(
+            fn=clear_and_save_textbox,
+            inputs=textbox,
+            outputs=[textbox, saved_input],
+            api_name=False,
+            queue=False,
+        )
+        .then(
+            fn=check_input_token_length,
+            inputs=[saved_input, chatbot, system_prompt],
+            api_name=False,
+            queue=False,
+        )
+        .success(
+            fn=display_input,
+            inputs=[saved_input, chatbot],
+            outputs=chatbot,
+            api_name=False,
+            queue=False,
+        )
+        .then(
+            fn=assign_uuid,
+            inputs=[chatbot, uuid_list],
+            outputs=uuid_list,
+        )
+        .then(
+            fn=output_log,
+            inputs=[chatbot, uuid_list],
+        )
+        .success(
+            fn=generate,
+            inputs=[
+                saved_input,
+                chatbot,
+                system_prompt,
+                max_new_tokens,
+                temperature,
+                top_p,
+                top_k,
+                do_sample,
+                repetition_penalty,
+            ],
+            outputs=chatbot,
+            api_name=False,
+        )
+        .then(
+            fn=assign_uuid,
+            inputs=[chatbot, uuid_list],
+            outputs=uuid_list,
+        )
+        .then(
+            fn=output_log,
+            inputs=[chatbot, uuid_list],
+        )
+        .then(
+            fn=convert_history_to_str,
+            inputs=chatbot,
+            outputs=output_textbox,
+        )
+    )
+
+    retry_button.click(
+        fn=delete_prev_fn,
+        inputs=chatbot,
+        outputs=[chatbot, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=check_input_token_length,
+        inputs=[saved_input, chatbot, system_prompt],
+        api_name=False,
+        queue=False,
+    ).success(
+        fn=display_input,
+        inputs=[saved_input, chatbot],
+        outputs=chatbot,
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=assign_uuid,
+        inputs=[chatbot, uuid_list],
+        outputs=uuid_list,
+    ).then(
+        fn=output_log,
+        inputs=[chatbot, uuid_list],
+    ).then(
+        fn=generate,
+        inputs=[
+            saved_input,
+            chatbot,
+            system_prompt,
+            max_new_tokens,
+            temperature,
+            top_p,
+            top_k,
+            do_sample,
+            repetition_penalty,
+        ],
+        outputs=chatbot,
+        api_name=False,
+    ).then(
+        fn=assign_uuid,
+        inputs=[chatbot, uuid_list],
+        outputs=uuid_list,
+    ).then(
+        fn=output_log,
+        inputs=[chatbot, uuid_list],
+    ).then(
+        fn=convert_history_to_str,
+        inputs=chatbot,
+        outputs=output_textbox,
+    )
+
+    undo_button.click(
+        fn=delete_prev_fn,
+        inputs=chatbot,
+        outputs=[chatbot, saved_input],
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=assign_uuid,
+        inputs=[chatbot, uuid_list],
+        outputs=uuid_list,
+    ).then(
+        fn=lambda x: x,
+        inputs=saved_input,
+        outputs=textbox,
+        api_name=False,
+        queue=False,
+    ).then(
+        fn=convert_history_to_str,
+        inputs=chatbot,
+        outputs=output_textbox,
+    )
+
+    clear_button.click(
+        fn=lambda: ([], ''),
+        outputs=[chatbot, saved_input],
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=assign_uuid,
+        inputs=[chatbot, uuid_list],
+        outputs=uuid_list,
+    ).then(
+        fn=convert_history_to_str,
+        inputs=chatbot,
+        outputs=output_textbox,
+    )
+
+demo.queue(max_size=5).launch(server_name='0.0.0.0')

model_vllm.py

@@ -0,0 +1,115 @@
+from typing import Iterator, AsyncGenerator
+import json
+import logging
+
+from transformers import AutoTokenizer
+from vllm.engine.arg_utils import AsyncEngineArgs
+from vllm.engine.async_llm_engine import AsyncLLMEngine
+from vllm.sampling_params import SamplingParams
+from vllm.utils import random_uuid
+
+logger = logging.getLogger(__name__)
+
+
+# Initialize the LLM Engine
+def init_engine():
+    engine_args = AsyncEngineArgs(model=model_id, dtype='bfloat16', disable_log_requests=True, disable_log_stats=True)
+    engine = AsyncLLMEngine.from_engine_args(engine_args)
+
+    return engine
+
+
+model_id = 'elyza/ELYZA-japanese-Llama-2-13b-instruct'
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+engine = init_engine()
+
+
+# Generator function for streaming response
+async def stream_results(prompt, sampling_params):
+    global engine
+    request_id = random_uuid()
+    results_generator = engine.generate(prompt, sampling_params, request_id)
+
+    async for request_output in results_generator:
+        text_outputs = [output.text for output in request_output.outputs]
+        yield text_outputs
+
+
+def get_prompt(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> str:
+    texts = [f'<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
+    # The first user input is _not_ stripped
+    do_strip = False
+    for user_input, response in chat_history:
+        user_input = user_input.strip() if do_strip else user_input
+        do_strip = True
+        texts.append(f'{user_input} [/INST] {response.strip()} </s><s>[INST] ')
+    message = message.strip() if do_strip else message
+    texts.append(f'{message} [/INST]')
+    return ''.join(texts)
+
+
+def get_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> int:
+    prompt = get_prompt(message, chat_history, system_prompt)
+    input_ids = tokenizer([prompt], return_tensors='np', add_special_tokens=False)['input_ids']
+    return input_ids.shape[-1]
+
+
+# Function to generate a response
+async def generate_response(engine, prompt: str):
+    request_id = random_uuid()
+    sampling_params = SamplingParams()
+    results_generator = engine.generate(prompt, sampling_params, request_id)
+
+    final_output = None
+    async for request_output in results_generator:
+        final_output = request_output
+
+    assert final_output is not None
+    text_outputs = [output.text for output in final_output.outputs]
+    return text_outputs
+
+
+async def run(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int = 1024,
+    temperature: float = 0.8,
+    top_p: float = 0.95,
+    top_k: int = 50,
+    do_sample: bool = False,
+    repetition_penalty: float = 1.2,
+    stream: bool = False,
+) -> AsyncGenerator | str:
+    request_id = random_uuid()
+    prompt = get_prompt(message=message, chat_history=chat_history, system_prompt=system_prompt)
+
+    if not do_sample:
+        # greedy
+        temperature = 0
+    sampling_params = SamplingParams(
+        max_tokens=max_new_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        top_k=top_k,
+        repetition_penalty=repetition_penalty,
+    )
+
+    logger.info(f'queue: {request_id}')
+    results_generator = engine.generate(
+        prompt=prompt,
+        sampling_params=sampling_params,
+        request_id=request_id,
+    )
+
+    # Streaming case
+    async def stream_results() -> AsyncGenerator:
+        async for request_output in results_generator:
+            yield ''.join([output.text for output in request_output.outputs])
+
+    if stream:
+        return stream_results()
+    else:
+        async for request_output in results_generator:
+            pass
+        return ''.join([output.text for output in request_output.outputs])

requirements.txt

@@ -0,0 +1,153 @@
+accelerate==0.25.0
+aiofiles==23.2.1
+aiohttp==3.9.1
+aioprometheus==23.3.0
+aiosignal==1.3.1
+altair==5.2.0
+anyio==3.7.1
+asttokens==2.4.1
+attrs==23.1.0
+auto-gptq==0.6.0
+bitsandbytes==0.41.3.post2
+boto3==1.34.7
+botocore==1.34.7
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+coloredlogs==15.0.1
+comm==0.2.0
+contourpy==1.2.0
+coverage==7.3.4
+cycler==0.12.1
+datasets==2.14.4
+debugpy==1.8.0
+decorator==5.1.1
+dill==0.3.7
+distlib==0.3.8
+executing==2.0.1
+fastapi==0.105.0
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.47.0
+frozenlist==1.4.1
+fsspec==2023.12.2
+gekko==1.0.6
+gradio==3.50.2
+gradio_client==0.6.1
+h11==0.14.0
+httpcore==1.0.2
+httptools==0.6.1
+httpx==0.26.0
+huggingface-hub==0.20.1
+humanfriendly==10.0
+idna==3.6
+importlib-resources==6.1.1
+iniconfig==2.0.0
+ipykernel==6.27.1
+ipython==8.19.0
+isort==5.13.2
+jedi==0.19.1
+Jinja2==3.1.2
+jmespath==1.0.1
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+jupyter_client==8.6.0
+jupyter_core==5.5.1
+kiwisolver==1.4.5
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+matplotlib-inline==0.1.6
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+multiprocess==0.70.15
+mypy==1.8.0
+mypy-extensions==1.0.0
+nest-asyncio==1.5.8
+networkx==3.2.1
+ninja==1.11.1.1
+numpy==1.26.2
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+optimum==1.16.1
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+parso==0.8.3
+peft==0.7.1
+pexpect==4.9.0
+Pillow==10.1.0
+platformdirs==4.1.0
+pluggy==1.3.0
+prompt-toolkit==3.0.43
+protobuf==4.25.1
+psutil==5.9.7
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py==1.11.0
+pyarrow==14.0.2
+pydantic==1.10.13
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+pytest==7.4.3
+pytest-cov==2.12.1
+pytest-mock==3.12.0
+pytest-mypy==0.9.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+pyzmq==25.1.2
+quantile-python==1.1
+ray==2.9.0
+referencing==0.32.0
+regex==2023.10.3
+requests==2.31.0
+rouge==1.0.1
+rpds-py==0.15.2
+ruff==0.1.9
+s3transfer==0.10.0
+safetensors==0.4.1
+semantic-version==2.10.0
+sentencepiece==0.1.99
+six==1.16.0
+sniffio==1.3.0
+stack-data==0.6.3
+starlette==0.27.0
+sympy==1.12
+tokenizers==0.15.0
+toml==0.10.2
+toolz==0.12.0
+torch==2.1.2
+tornado==6.4
+tox==3.28.0
+tqdm==4.66.1
+traitlets==5.14.0
+transformers==4.36.2
+triton==2.1.0
+typing_extensions==4.9.0
+tzdata==2023.3
+urllib3==2.0.7
+uvicorn==0.25.0
+uvloop==0.19.0
+virtualenv==20.25.0
+vllm==0.2.6
+watchfiles==0.21.0
+wcwidth==0.2.12
+websockets==11.0.3
+xformers==0.0.23.post1
+xxhash==3.4.1
+yarl==1.9.4

style.css

@@ -0,0 +1,23 @@
+h1 {
+  text-align: center;
+}
+
+#logo {
+  display: flex;
+  justify-content: center;
+  align-items: center;
+  gap: 50px;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+
+#component-0 {
+  max-width: 900px;
+  margin: auto;
+  padding-top: 1.5rem;
+}