Honyaku 7b V2

🚀 Honyaku-7b-v2

Honyaku-7b-v2是其前作的改进版本。与之前的版本相比，该模型在遵循多语言生成标签方面表现出更高的准确性。

🚀 快速开始

Honyaku-7b-v2是一个强大的多语言翻译模型，以下是使用它进行翻译的不同示例代码，你可以根据自己的需求选择合适的方式。

✨ 主要特性

• 多语言生成精度提升：该模型在遵循多语言生成标签方面的精度有所提高。
• 反映翻译质量：Honyaku-7b的翻译质量受基础模型预训练的影响很大。因此，翻译质量与原始语言模型的训练量成正比。
• 主要翻译范围：主要用于翻译约500到数千个标记的文本。由于基础模型的特性，翻译成日语最为稳定。
• 标记支持范围：该模型已针对最多8k个标记进行了微调，但基于基础模型的特性，包括提示在内，最多支持4k个标记。

⚠️ 注意事项

⚠️ 重要提示

• 在小语种翻译方面，该模型的表现不佳。
• 7b级别的大语言模型（LLM）的翻译功能往往存在错误。请勿将未经检查的文本用于社交沟通。

📦 安装指南

文档中未提及安装步骤，故跳过此章节。

💻 使用示例

基础用法

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

# 语言列表
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界面的设置
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()

高级用法

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)

# 定义流处理器
streamer = TextStreamer(tokenizer)

# 定义英文提示
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.
"""

# 准备从英语到日语翻译的提示
prompt = f"<english>: {english_prompt} </english>\n\n<japanese>:"

# 对输入文本进行分词并移动到CUDA设备
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# 使用模型和流处理器生成输出
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界面的设置
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,  # 明确通过点击按钮执行翻译
    allow_flagging=False
)

demo.launch()

📚 详细文档

文档中未提及详细说明内容，故跳过此章节。

🔧 技术细节

文档中未提及技术实现细节，故跳过此章节。

📄 许可证

本项目采用 Apache-2.0 许可证。

📚 基础模型

本模型基于 tokyotech-llm/Swallow-MS-7b-v0.1 构建。