Honyaku 7b V2

🚀 Honyaku-7b-v2

Honyaku-7b-v2是其前作的改進版本。與之前的版本相比，該模型在遵循多語言生成標籤方面表現出更高的準確性。

🚀 快速開始

Honyaku-7b-v2是一個強大的多語言翻譯模型，以下是使用它進行翻譯的不同示例代碼，你可以根據自己的需求選擇合適的方式。

✨ 主要特性

• 多語言生成精度提升：該模型在遵循多語言生成標籤方面的精度有所提高。
• 反映翻譯質量：Honyaku-7b的翻譯質量受基礎模型預訓練的影響很大。因此，翻譯質量與原始語言模型的訓練量成正比。
• 主要翻譯範圍：主要用於翻譯約500到數千個標記的文本。由於基礎模型的特性，翻譯成日語最為穩定。
• 標記支持範圍：該模型已針對最多8k個標記進行了微調，但基於基礎模型的特性，包括提示在內，最多支持4k個標記。

⚠️ 注意事項

⚠️ 重要提示

• 在小語種翻譯方面，該模型的表現不佳。
• 7b級別的大語言模型（LLM）的翻譯功能往往存在錯誤。請勿將未經檢查的文本用於社交溝通。

📦 安裝指南

文檔中未提及安裝步驟，故跳過此章節。

💻 使用示例

基礎用法

# Honyaku-7b-webui
import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
from threading import Thread

# 語言列表
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界面的設置
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()

高級用法

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)

# 定義流處理器
streamer = TextStreamer(tokenizer)

# 定義英文提示
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.
"""

# 準備從英語到日語翻譯的提示
prompt = f"<english>: {english_prompt} </english>\n\n<japanese>:"

# 對輸入文本進行分詞並移動到CUDA設備
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# 使用模型和流處理器生成輸出
output = model.generate(**inputs, max_new_tokens=4096, do_sample=True, top_k=20, top_p=0.95, streamer=streamer)

Gradio非流式生成

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界面的設置
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,  # 明確通過點擊按鈕執行翻譯
    allow_flagging=False
)

demo.launch()

📚 詳細文檔

文檔中未提及詳細說明內容，故跳過此章節。

🔧 技術細節

文檔中未提及技術實現細節，故跳過此章節。

📄 許可證

本項目採用 Apache-2.0 許可證。

📚 基礎模型

本模型基於 tokyotech-llm/Swallow-MS-7b-v0.1 構建。