Honyaku 7b V2

🚀 Honyaku-7b-v2

Honyaku-7b-v2は、前バージョンを改良したモデルです。多言語生成タグへの追従精度が向上し、翻訳品質も安定しています。主に500～数千トークンの翻訳を目的としており、日本語への翻訳が最も安定しています。

✨ 主な機能

• 多言語生成の精度向上：モデルは、多言語生成タグに対する追従の精度が向上しました。
• 翻訳品質の反映：Honyaku-7bの翻訳品質は、ベースモデルの事前学習に強く影響されます。翻訳品質は、元の言語モデルの学習量に比例して変わります。
• 特定トークン範囲の翻訳：500～数1000 tokenの翻訳を主目的としています。ただし、短すぎる文や長すぎる文では性能が低下することがあります。
• 日本語翻訳の安定性：Base modelの特徴から、日本語への翻訳が最も安定しています。
• トークン対応範囲：8k tokenまでファインチューニングしていますが、Base modelの特徴からprompt含めて4k tokenにまで対応とします。

⚠️ 注意事項

• マイナー言語の翻訳機能：マイナーな言語においては、翻訳がうまく機能しません。
• 7bレベルLLMの誤り：7bレベルの大規模言語モデル(LLM)の翻訳機能には誤りが多くみられます。未チェックの文章は、正式なコミュニケーションには使用しないでください。

💻 使用例

基本的な使用法

import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
from threading import Thread

# 言語リスト
languages = [
    "English", "Chinese (Simplified)", "Chinese (Traditional)", "Spanish", "Arabic", "Hindi",
    "Bengali", "Portuguese", "Russian", "Japanese", "German", "French", "Urdu", "Indonesian",
    "Italian", "Turkish", "Korean", "Vietnamese", "Tamil", "Marathi", "Telugu", "Persian",
    "Polish", "Dutch", "Thai", "Gujarati", "Romanian", "Ukrainian", "Malay", "Kannada", "Oriya (Odia)",
    "Burmese (Myanmar)", "Azerbaijani", "Uzbek", "Kurdish (Kurmanji)", "Swedish", "Filipino (Tagalog)",
    "Serbian", "Czech", "Hungarian", "Greek", "Belarusian", "Bulgarian", "Hebrew", "Finnish",
    "Slovak", "Norwegian", "Danish", "Sinhala", "Croatian", "Lithuanian", "Slovenian", "Latvian",
    "Estonian", "Armenian", "Malayalam", "Georgian", "Mongolian", "Afrikaans", "Nepali", "Pashto",
    "Punjabi", "Kurdish", "Kyrgyz", "Somali", "Albanian", "Icelandic", "Basque", "Luxembourgish",
    "Macedonian", "Maltese", "Hawaiian", "Yoruba", "Maori", "Zulu", "Welsh", "Swahili", "Haitian Creole",
    "Lao", "Amharic", "Khmer", "Javanese", "Kazakh", "Malagasy", "Sindhi", "Sundanese", "Tajik", "Xhosa",
    "Yiddish", "Bosnian", "Cebuano", "Chichewa", "Corsican", "Esperanto", "Frisian", "Galician", "Hausa",
    "Hmong", "Igbo", "Irish", "Kinyarwanda", "Latin", "Samoan", "Scots Gaelic", "Sesotho", "Shona",
    "Sotho", "Swedish", "Uyghur"
]

tokenizer = AutoTokenizer.from_pretrained("aixsatoshi/Honyaku-7b-v2")
model = AutoModelForCausalLM.from_pretrained("aixsatoshi/Honyaku-7b-v2", torch_dtype=torch.float16)
model = model.to('cuda:0')

class StopOnTokens(StoppingCriteria):
    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
        stop_ids = [2]
        for stop_id in stop_ids:
            if input_ids[0][-1] == stop_id:
                return True
        return False

def predict(message, history, tokens, temperature, language):
    tag = "<" + language.lower() + ">"
    history_transformer_format = history + [[message, ""]]
    stop = StopOnTokens()

    messages = "".join(["".join(["\n<english>:"+item[0]+"</english>\n", tag+item[1]])
                for item in history_transformer_format])

    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
    generate_kwargs = dict(
        model_inputs,
        streamer=streamer,
        max_new_tokens=int(tokens),
        temperature=float(temperature),
        do_sample=True,
        top_p=0.95,
        top_k=20,
        repetition_penalty=1.15,
        num_beams=1,
        stopping_criteria=StoppingCriteriaList([stop])
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    partial_message = ""
    for new_token in streamer:
        if new_token != '<':
            partial_message += new_token
            yield partial_message

# Gradioインタフェースの設定
demo = gr.ChatInterface(
    fn=predict, 
    title="Honyaku-7b webui",
    description="Translate using Honyaku-7b model",
    additional_inputs=[
        gr.Slider(100, 4096, value=1000, label="Tokens"),
        gr.Slider(0.0, 1.0, value=0.3, label="Temperature"),
        gr.Dropdown(choices=languages, value="Japanese", label="Language")
    ]
)

demo.queue().launch()

高度な使用法

Textstreamer

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_name = "aixsatoshi/Honyaku-7b-v2"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the streamer
streamer = TextStreamer(tokenizer)

# Define the English prompt
english_prompt = """
Machine translation accuracy varies greatly across languages.
Key challenges include context understanding, idiomatic expressions, and syntactic differences.
Advanced models leverage AI to enhance translation quality, focusing on nuances and cultural relevance.

To address these challenges, developers employ neural networks and deep learning techniques, which adapt to linguistic variations and learn from vast amounts of text.
This approach helps in capturing the essence of languages and accurately translating complex sentences.

Furthermore, user feedback plays a crucial role in refining translation algorithms.
By analyzing corrections and suggestions, machine translation systems can evolve and handle nuanced expressions more effectively.
This iterative process ensures continuous improvement, making translations more reliable and understandable for a global audience.
"""

# Prepare the prompt for English to Japanese translation
prompt = f"<english>: {english_prompt} </english>\n\n<japanese>:"

# Tokenize the input text and move to CUDA device
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Generate the output using the model and streamer
output = model.generate(**inputs, max_new_tokens=4096, do_sample=True, top_k=20, top_p=0.95, streamer=streamer)

Gradio non - streaming generation

import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

languages = [
    "English", "Chinese (Simplified)", "Chinese (Traditional)", "Spanish", "Arabic", "Hindi",
    "Bengali", "Portuguese", "Russian", "Japanese", "German", "French", "Urdu", "Indonesian",
    "Italian", "Turkish", "Korean", "Vietnamese", "Tamil", "Marathi", "Telugu", "Persian",
    "Polish", "Dutch", "Thai", "Gujarati", "Romanian", "Ukrainian", "Malay", "Kannada", "Oriya (Odia)",
    "Burmese (Myanmar)", "Azerbaijani", "Uzbek", "Kurdish (Kurmanji)", "Swedish", "Filipino (Tagalog)",
    "Serbian", "Czech", "Hungarian", "Greek", "Belarusian", "Bulgarian", "Hebrew", "Finnish",
    "Slovak", "Norwegian", "Danish", "Sinhala", "Croatian", "Lithuanian", "Slovenian", "Latvian",
    "Estonian", "Armenian", "Malayalam", "Georgian", "Mongolian", "Afrikaans", "Nepali", "Pashto",
    "Punjabi", "Kurdish", "Kyrgyz", "Somali", "Albanian", "Icelandic", "Basque", "Luxembourgish",
    "Macedonian", "Maltese", "Hawaiian", "Yoruba", "Maori", "Zulu", "Welsh", "Swahili", "Haitian Creole",
    "Lao", "Amharic", "Khmer", "Javanese", "Kazakh", "Malagasy", "Sindhi", "Sundanese", "Tajik", "Xhosa",
    "Yiddish", "Bosnian", "Cebuano", "Chichewa", "Corsican", "Esperanto", "Frisian", "Galician", "Hausa",
    "Hmong", "Igbo", "Irish", "Kinyarwanda", "Latin", "Samoan", "Scots Gaelic", "Sesotho", "Shona",
    "Sotho", "Swedish", "Uyghur"
]

tokenizer = AutoTokenizer.from_pretrained("aixsatoshi/Honyaku-7b-v2")
model = AutoModelForCausalLM.from_pretrained("aixsatoshi/Honyaku-7b-v2", torch_dtype=torch.float16)
model = model.to('cuda:0')

def predict(message, tokens, temperature, language):
    tag = "<" + language.lower() + ">"
    messages = "\n<english>:" + message + "</english>\n" + tag

    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
    output = model.generate(
        **model_inputs,
        max_new_tokens=int(tokens),
        temperature=float(temperature),
        do_sample=True,
        top_p=0.95,
        top_k=20,
        repetition_penalty=1.15,
        num_beams=1,
        eos_token_id=tokenizer.eos_token_id
    )
    translation = tokenizer.decode(output[0], skip_special_tokens=True)
    return translation

# Gradioインタフェースの設定
inputs = [
    gr.Textbox(label="Message", lines=20),
    gr.Slider(100, 4096, value=1000, label="Tokens"),
    gr.Slider(0.0, 1.0, value=0.3, label="Temperature"),
    gr.Dropdown(choices=languages, value="Japanese", label="Language")
]
output = gr.Textbox(label="Translation", lines=35)

demo = gr.Interface(
    fn=predict,
    inputs=inputs,
    outputs=output,
    title="Honyaku-7b webui",
    description="Translate using Honyaku-7b model",
    live=False,  # 明示的にボタンをクリックして翻訳を実行する
    allow_flagging=False
)

demo.launch()

📚 ベースモデル

tokyotech-llm/Swallow-MS-7b-v0.1

📄 ライセンス

Apache-2.0