File score_MMLU.py

evaluation/score_MMLU.py:None–None · view source on GitHub ↗

Source from the content-addressed store, hash-verified

1	import pandas as pd
2	import os,torch,re,jsonlines
3	from tqdm import tqdm
4	from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig

nothing calls this directly

get_few_shot_promptFunction · 0.85

get_input_dataFunction · 0.85

get_capital_answerFunction · 0.85

from_pretrainedMethod · 0.80

evalMethod · 0.80

chatMethod · 0.45

appendMethod · 0.45

no test coverage detected