Is there the code for downstream task in this project？

Question

Is there the code for downstream task in this project？

Claymore715 opened this issue 2 years ago · comments

Claymore715 commented 2 years ago

to compare the efficiency between manual prompt and autoprompt

Claymore715 · Answer 1 · Mon May 09 2022 09:49:46 GMT+0800 (China Standard Time)

for example，how to test the performance for task Sentiment Analysis

Taylor Shin · Answer 2 · Tue May 10 2022 01:53:03 GMT+0800 (China Standard Time)

For evaluation of prompts for fact retrieval and relation extraction, refer to this section of the README. For the other tasks, you'll have to write some code that will load the eval dataset (SST-2 or SICK-E), append the trigger tokens, feed the full prompt into the LM, and score the results.