Commit c6b5510c authored by LucWeber's avatar LucWeber
Browse files

Add acknowledgements

parent ef2c359f
...@@ -10,6 +10,8 @@ The versatility of large language models (LLMs) led to the creation of diverse b ...@@ -10,6 +10,8 @@ The versatility of large language models (LLMs) led to the creation of diverse b
Homepage: - Homepage: -
All configs and utils mirror the ones from their original dataset!
### Groups and Tasks ### Groups and Tasks
#### Groups #### Groups
...@@ -95,6 +97,7 @@ Estimating performance for each scenario all at once ...@@ -95,6 +97,7 @@ Estimating performance for each scenario all at once
} }
``` ```
Please also reference the respective original dataset that you are using!
### Checklist ### Checklist
......
import datasets import datasets
import re import re
''' This code mirrors the utils of the original hellaswag task '''
def preprocess(text): def preprocess(text):
text = text.strip() text = text.strip()
......
...@@ -4,6 +4,7 @@ import numpy as np ...@@ -4,6 +4,7 @@ import numpy as np
from rouge_score import rouge_scorer, scoring from rouge_score import rouge_scorer, scoring
''' This code mirrors the utils of the original truthful_qa task '''
def process_results_mc2(doc, results): def process_results_mc2(doc, results):
lls, is_greedy = zip(*results) lls, is_greedy = zip(*results)
......
''' This code mirrors the utils of the original winogrande task '''
def doc_to_text(doc): def doc_to_text(doc):
answer_to_num = {"1": 0, "2": 1} answer_to_num = {"1": 0, "2": 1}
return answer_to_num[doc["answer"]] return answer_to_num[doc["answer"]]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment