mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
7a7a4517ab
* bigcodebench * humaneval * humanevalx * humanevalx * livecodebench * mbpp * humaneval_plus * fix bug * template * max_out fix * template update
45 lines
2.9 KiB
Python
45 lines
2.9 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
from opencompass.datasets import MBPPDataset, MBPPEvaluator
|
|
|
|
mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_list_2')
|
|
|
|
mbpp_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
round=[
|
|
dict(role='HUMAN', prompt='You are an expert Python programmer, and here is your task: Write a function to find the similar elements from the given two tuple lists. Your code should pass these tests:\n\n assert similar_elements((3, 4, 5, 6),(5, 7, 4, 10)) == (4, 5)\nassert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \nassert similar_elements((11, 12, 14, 13),(17, 15, 14, 13)) == (13, 14) \n'),
|
|
dict(role='BOT', prompt="[BEGIN]\n 'def similar_elements(test_tup1, test_tup2):\r\n res = tuple(set(test_tup1) & set(test_tup2))\r\n return (res)' \n[DONE] \n\n "),
|
|
|
|
dict(role='HUMAN', prompt='You are an expert Python programmer, and here is your task: Write a python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \nassert is_not_prime(10) == True \nassert is_not_prime(35) == True \n'),
|
|
dict(role='BOT', prompt="[BEGIN]\n 'import math\r\ndef is_not_prime(n):\r\n result = False\r\n for i in range(2,int(math.sqrt(n)) + 1):\r\n if n % i == 0:\r\n result = True\r\n return result' \n[DONE] \n\n "),
|
|
|
|
dict(role='HUMAN', prompt='You are an expert Python programmer, and here is your task: Write a function to find the largest integers from a given list of numbers using heap queue algorithm. Your code should pass these tests:\n\n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],3)==[85, 75, 65] \nassert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \nassert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],5)==[85, 75, 65, 58, 35] \n'),
|
|
dict(role='BOT', prompt="[BEGIN]\n 'import heapq as hq\r\ndef heap_queue_largest(nums,n):\r\n largest_nums = hq.nlargest(n, nums)\r\n return largest_nums' \n[DONE] \n\n "),
|
|
|
|
dict(role='HUMAN', prompt='You are an expert Python programmer, and here is your task: {text} Your code should pass these tests:\n\n {test_list} \n'),
|
|
dict(role='BOT', prompt='[BEGIN]\n'),
|
|
],
|
|
),
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer),
|
|
)
|
|
|
|
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
|
|
|
|
mbpp_datasets = [
|
|
dict(
|
|
type=MBPPDataset,
|
|
abbr='mbpp',
|
|
path='opencompass/mbpp',
|
|
reader_cfg=mbpp_reader_cfg,
|
|
infer_cfg=mbpp_infer_cfg,
|
|
eval_cfg=mbpp_eval_cfg,
|
|
n=5,
|
|
k=3
|
|
)
|
|
]
|