add MMLU and C-Eval script

This commit is contained in:
hiyouga
2023-09-23 00:34:17 +08:00
parent 5cc7a44784
commit 465ee8119a
16 changed files with 1019 additions and 856 deletions

View File

@@ -138,12 +138,11 @@ class Template:
token_ids = []
for elem in context:
if isinstance(elem, str):
if len(elem) == 0:
continue
elem = elem.replace("{{system}}", system, 1) if system is not None else elem
elem = elem.replace("{{query}}", query, 1) if query is not None else elem
elem = elem.replace("{{idx}}", idx, 1) if idx is not None else elem
token_ids = token_ids + tokenizer.encode(elem, **kwargs)
if len(elem) != 0:
token_ids = token_ids + tokenizer.encode(elem, **kwargs)
elif isinstance(elem, dict):
token_ids = token_ids + [tokenizer.convert_tokens_to_ids(elem.get("token"))]
else: