一、项目介绍

此项目是参考github上优秀的机器翻译项目mRASP2,将官方开源的fairseq预训练权重改写为transformers架构,使其能够更加方便使用。

二、使用方法

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model_path = 'ENLP/mrasp2'
model = AutoModelForSeq2SeqLM.from_pretrained(model_path, trust_remote_code=True, cache_dir=model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, cache_dir=model_path)
input_text = ["Welcome to download and use!"]
inputs = tokenizer(input_text, return_tensors="pt", padding=True, max_length=1024, truncation=True)
result = model.generate(**inputs)
result = tokenizer.batch_decode(result, skip_special_tokens=True)
result = [pre.strip() for pre in result]
# ['欢迎下载和使用!']

三、使用说明

该模型支持32种语言,更多详细参考mRASP2,此模型库的tokenizer仅针对中英双语进行优化,如果需要使用其他语言请 自行参考tokenization_bat.py进行修改。请注意,这是官方的6e6d-no-mono模型,12e12d两个模型暂时无法实现,找不到原因,如果有知道的小伙伴可以分享出来。

四、其他模型

ENLP/mrasp

Downloads last month
11
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.