1. 定義任務(wù)

from openprompt.data_utils import InputExample classes=['negative','positive' ]dataset=[InputExample(guid = 0,text_a = "Albert Einstein was one of the greatest intellects of his time.",),InputExample(guid = 1,text_a = "The film was badly made.",), ]

2. 定義預(yù)訓(xùn)練語(yǔ)言模型

from openprompt.plms import load_plm plm,tokenizer,model_config,WrapperClass=load_plm('bert',"bert-base-cased")

3. 定義prompt模板

from openprompt.prompts import ManualTemplate promptTemplate=ManualTemplate(text='{"placeholder":"text_a"} It was {"mask"}',tokenizer=tokenizer, )

4. 定義輸出-label映射

from openprompt.prompts import ManualVerbalizer promptVerbalizer=ManualVerbalizer(classes=classes,label_words={'negative':['bad'],'positive':['good','wonderful','great'],},tokenizer=tokenizer, )

5. 組合構(gòu)建為PromptModel類(lèi)

from openprompt import PromptForClassification promptModel=PromptForClassification(template=promptTemplate,plm=plm,verbalizer=promptVerbalizer, )

6. 定義dataloader

from openprompt import PromptDataLoader data_loader=PromptDataLoader(dataset=dataset,tokenizer=tokenizer,template=promptTemplate,tokenizer_wrapper_class=WrapperClass, )

7. 開(kāi)始訓(xùn)練、測(cè)試

# making zero-shot inference using pretrained MLM with prompt promptModel.eval() with torch.no_grad():for batch in data_loader:logits=promptModel(batch)preds=torch.argmax(logits,dim=-1)print(classes[preds])# predictions would be 1, 0 for classes 'positive', 'negative'

參考知乎

總結(jié)

以上是生活随笔為你收集整理的prompt 代码示例的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。