语言: 韩语
标签:

• bert
• mrc
  数据集:
• klue
  许可协议: cc-by-sa-4.0

用于问答任务的bert-base模型

代码: 参见 Ainize Workspace

klue-bert-base-mrc演示: Ainize演示

klue-bert-base-mrc API: Ainize API

概述

语言模型: klue/bert-base
语言: 韩语
下游任务: 抽取式问答
训练数据: KLUE-MRC
评估数据: KLUE-MRC

使用方法

在Transformers中使用

from transformers import AutoModelForQuestionAnswering, AutoTokenizer  

tokenizer = AutoTokenizer.from_pretrained("ainize/klue-bert-base-mrc")  
model = AutoModelForQuestionAnswering.from_pretrained("ainize/klue-bert-base-mrc")  

context = "上下文内容"  
question = "问题内容"  

encodings = tokenizer(context, question, max_length=512, truncation=True,  
                      padding="max_length", return_token_type_ids=False)  
encodings = {key: torch.tensor([val]) for key, val in encodings.items()}               

input_ids = encodings["input_ids"]  
attention_mask = encodings["attention_mask"]  

pred = model(input_ids, attention_mask=attention_mask)  

start_logits, end_logits = pred.start_logits, pred.end_logits  

token_start_index, token_end_index = start_logits.argmax(dim=-1), end_logits.argmax(dim=-1)  

pred_ids = input_ids[0][token_start_index: token_end_index + 1]  

prediction = tokenizer.decode(pred_ids)  

关于我们

Teachable NLP - 无需编写代码即可使用自有文本训练NLP模型
Ainize - 使用免费GPU部署机器学习项目