You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

22 lines
578 B
Python

import datasets
from benchmarks.overall.methods import BaseMethod, BenchmarkResult
class MathpixMethod(BaseMethod):
mathpix_ds: datasets.Dataset = None
def __call__(self, sample) -> BenchmarkResult:
uuid = sample["uuid"]
data = None
for row in self.mathpix_ds:
if str(row["uuid"]) == str(uuid):
data = row
break
if not data:
raise ValueError(f"Could not find data for uuid {uuid}")
return {
"markdown": data["md"],
"time": data["time"]
}