title = content.split("\n")[0].replace("// ", "")
if title in titles_to_be_excluded:
continue
ckpts = set(x.lower().strip()
for x in re.findall(r"\[model\]\((https?.*)\)", content))
if len(ckpts) == 0:
After Change
continue
_papertype = [x for x in re.findall(r"\[([A-Z]+)\]", content)]
assert len(_papertype) > 0
papertype = _papertype[0]
paper = set([(papertype, title)])