Files
Open-Assistant/model/supervised_finetuning/custom_datasets/formatting.py
T
Sotirios Anagnostidis 6a68139b91 os private dataset
2023-02-11 13:20:42 +01:00

12 lines
371 B
Python

QA_SPECIAL_TOKENS = {"Question": "<human>", "Answer": "<bot>", "StartPrefix": "<prefix>", "EndPrefix": "</prefix>"}
def format_pair(pairs):
assert len(pairs) % 2 == 0
return [
"{}{}{}".format(QA_SPECIAL_TOKENS["Question"], pairs[i], QA_SPECIAL_TOKENS["Answer"])
if i % 2 == 0
else pairs[i]
for i in range(0, len(pairs), 2)
]