mt5-small-translation-ja_zh

测试用colab笔记，test notebook

不需要自己装环境即可使用！！No environment needed, use colab to test <br> https://colab.research.google.com/drive/1PA30HPgRooCTV-H9Wr_DZXHqC42PrgTO?usp=sharing <br> 现在翻译能力就是人工吗喽，不是词汇不够，是学不会了 <br> this model has problem learning more due to the 300M size and my poor techniques

模型公开声明

• 这个模型由 mt5-translation-ja_zh 启发（其实就是在它上面改的），使用mt5-small，整体较小
• 使用了CCMatrix-v1-Ja_Zh， 1e-4学习率， 7 个epoch, 大概1.7的 val loss，下不去了

Release Notes

• this model is finetuned from mt5-small, training methods and datasets refers to larryvrh/mt5-translation-ja_zh
• used a trimmed and fused dataset CCMatrix-v1-Ja_Zh 1e-4 for 7 epoch no weight decay，arraived at about 1.7 val loss, it somehow stalls there

A more precise example using it

使用指南

from transformers import pipeline
model_name="iryneko571/mt5-small-translation-ja_zh"
#pipe = pipeline("translation",model=model_name,tokenizer=model_name,repetition_penalty=1.4,batch_size=1,max_length=256)
pipe = pipeline("translation",
  model=model_name,
  repetition_penalty=1.4,
  batch_size=1,
  max_length=256
  )

def translate_batch(batch, language='<-ja2zh->'): # batch is an array of string
    i=0 # quickly format the list
    while i<len(batch):
        batch[i]=f'{language} {batch[i]}'
        i+=1
    translated=pipe(batch)
    result=[]
    i=0
    while i<len(translated):
        result.append(translated[i]['translation_text'])
        i+=1
    return result

inputs=[]

print(translate_batch(inputs))