Unverified Commit aa2dd2b5 authored by Fengzhe Zhou's avatar Fengzhe Zhou Committed by GitHub
Browse files

[Format] Add config lints (#892)

parent 3dbba119
......@@ -18,7 +18,7 @@ math_infer_cfg = dict(
type=PromptTemplate,
template=dict(round=[
dict(role="HUMAN", prompt=QUERY_TEMPLATE),
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))
......
......@@ -9,15 +9,15 @@ math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(role="HUMAN", prompt="Problem:\nFind the domain of the expression $\\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}}\nSolution:"),
dict(role="BOT", prompt="The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\\boxed{{[2,5)}}$.\nFinal Answer: The final answer is $[2,5)$. I hope it is correct.\n"),
dict(role="HUMAN", prompt="Problem:\nIf $\det \mathbf{{A}} = 2$ and $\det \mathbf{{B}} = 12,$ then find $\det (\mathbf{{A}} \mathbf{{B}}).$\nSolution:"),
dict(role="BOT", prompt="We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \\boxed{{24}}.$\nFinal Answer: The final answer is $24$. I hope it is correct.\n"),
dict(role="HUMAN", prompt="Problem:\nTerrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight?\nSolution:"),
dict(role="BOT", prompt="If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \\begin{{align*}} 30n&=480\\\\ \Rightarrow\qquad n&=480/30=\\boxed{{16}} \end{{align*}}\nFinal Answer: The final answer is $16$. I hope it is correct.\n"),
dict(role="HUMAN", prompt="Problem:\nIf the system of equations: \\begin{{align*}} 6x-4y&=a,\\\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\\frac{{a}}{{b}},$ assuming $b$ is nonzero.\nSolution:"),
dict(role="BOT", prompt="If we multiply the first equation by $-\\frac{{3}}{{2}}$, we obtain $$6y-9x=-\\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\\frac{{3}}{{2}}a=b\Rightarrow\\frac{{a}}{{b}}=\\boxed{{-\\frac{{2}}{{3}}}}.$$\nFinal Answer: The final answer is $-\\frac{{2}}{{3}}$. I hope it is correct.\n"),
dict(role="HUMAN", prompt="Problem:\n{problem}\nSolution:\n"),
dict(role='HUMAN', prompt='Problem:\nFind the domain of the expression $\\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}}\nSolution:'),
dict(role='BOT', prompt='The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\\boxed{{[2,5)}}$.\nFinal Answer: The final answer is $[2,5)$. I hope it is correct.\n'),
dict(role='HUMAN', prompt='Problem:\nIf $\det \mathbf{{A}} = 2$ and $\det \mathbf{{B}} = 12,$ then find $\det (\mathbf{{A}} \mathbf{{B}}).$\nSolution:'),
dict(role='BOT', prompt='We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \\boxed{{24}}.$\nFinal Answer: The final answer is $24$. I hope it is correct.\n'),
dict(role='HUMAN', prompt='Problem:\nTerrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight?\nSolution:'),
dict(role='BOT', prompt='If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \\begin{{align*}} 30n&=480\\\\ \Rightarrow\qquad n&=480/30=\\boxed{{16}} \end{{align*}}\nFinal Answer: The final answer is $16$. I hope it is correct.\n'),
dict(role='HUMAN', prompt='Problem:\nIf the system of equations: \\begin{{align*}} 6x-4y&=a,\\\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\\frac{{a}}{{b}},$ assuming $b$ is nonzero.\nSolution:'),
dict(role='BOT', prompt='If we multiply the first equation by $-\\frac{{3}}{{2}}$, we obtain $$6y-9x=-\\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\\frac{{3}}{{2}}a=b\Rightarrow\\frac{{a}}{{b}}=\\boxed{{-\\frac{{2}}{{3}}}}.$$\nFinal Answer: The final answer is $-\\frac{{2}}{{3}}$. I hope it is correct.\n'),
dict(role='HUMAN', prompt='Problem:\n{problem}\nSolution:\n'),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))
......
......@@ -16,7 +16,7 @@ math_infer_cfg = dict(
type=PromptTemplate,
template=dict(round=[
dict(role="HUMAN", prompt=QUERY_TEMPLATE),
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=1024))
......
......@@ -33,14 +33,14 @@ math401_eval_cfg = dict(
math401_datasets = [
dict(
abbr="math401",
abbr='math401',
type=MathBenchDataset,
path=f"./data/math401/",
path=f'./data/math401/',
with_circular=False,
name="cloze_en",
name='cloze_en',
reader_cfg=dict(
input_columns=["question"],
output_column="answer"
input_columns=['question'],
output_column='answer'
),
infer_cfg=math401_infer_cfg,
eval_cfg=math401_eval_cfg,
......
......@@ -3,24 +3,24 @@ 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_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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 \n assert is_not_prime(10) == True \n assert 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset,
abbr="mbpp",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp',
path='./data/mbpp/mbpp.jsonl',
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
eval_cfg=mbpp_eval_cfg,
......
......@@ -3,7 +3,7 @@ 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_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_list_2')
mbpp_infer_cfg = dict(
prompt_template=dict(
......@@ -19,8 +19,8 @@ mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator))
mbpp_datasets = [
dict(
type=MBPPDataset,
abbr="mbpp",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp',
path='./data/mbpp/mbpp.jsonl',
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
eval_cfg=mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ 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_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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert similar_elements((11, 12, 14, 13),(17, 15, 14, 13)) == (13, 14) \n\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n"),
dict(role="BOT", prompt="[BEGIN]\ndef 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert similar_elements((11, 12, 14, 13),(17, 15, 14, 13)) == (13, 14) \n\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n'),
dict(role='BOT', prompt='[BEGIN]\ndef 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 \n assert is_not_prime(10) == True \n assert is_not_prime(35) == True \n\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n"),
dict(role="BOT", prompt="[BEGIN]\nimport 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert is_not_prime(35) == True \n\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n'),
dict(role='BOT', prompt='[BEGIN]\nimport 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],5)==[85, 75, 65, 58, 35] \n\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n"),
dict(role="BOT", prompt="[BEGIN]\nimport 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],5)==[85, 75, 65, 58, 35] \n\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n'),
dict(role='BOT', prompt='[BEGIN]\nimport 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\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n"),
dict(role="BOT", prompt="[BEGIN]\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\nYour code should start with a [BEGIN] tag and end with a [DONE] tag.\n'),
dict(role='BOT', prompt='[BEGIN]\n'),
],
),
),
......@@ -28,13 +28,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset,
abbr="mbpp",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp',
path='./data/mbpp/mbpp.jsonl',
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
eval_cfg=mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MBPPDataset_V2, MBPPPassKEvaluator
mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 \n assert is_not_prime(10) == True \n assert 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset_V2,
abbr="mbpp_passk",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp_passk',
path='./data/mbpp/mbpp.jsonl',
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
eval_cfg=mbpp_eval_cfg,
......
......@@ -5,24 +5,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MBPPDataset_V2, MBPPPassKEvaluator
mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 \n assert is_not_prime(10) == True \n assert 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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"),
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'),
],
),
),
......@@ -30,13 +30,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset_V2,
abbr="mbpp_repeat10",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp_repeat10',
path='./data/mbpp/mbpp.jsonl',
num_repeats=10,
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_list_2")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_list_2')
sanitized_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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 \n assert is_not_prime(10) == True \n assert 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ sanitized_mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp',
path='./data/mbpp/sanitized-mbpp.jsonl',
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
eval_cfg=sanitized_mbpp_eval_cfg,
......
......@@ -3,7 +3,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_list_2")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_list_2')
sanitized_mbpp_infer_cfg = dict(
prompt_template=dict(
......@@ -67,13 +67,13 @@ You are an expert Python programmer, and here is your task: {text} Your code sho
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp',
path='./data/mbpp/sanitized-mbpp.jsonl',
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
eval_cfg=sanitized_mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPPassKEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
sanitized_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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 \n assert is_not_prime(10) == True \n assert 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ sanitized_mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp_passk",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp_passk',
path='./data/mbpp/sanitized-mbpp.jsonl',
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
eval_cfg=sanitized_mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPPassKEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
sanitized_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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 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)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert 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 \n assert is_not_prime(10) == True \n assert 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 python function to identify non-prime numbers. Your code should pass these tests:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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: 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] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ sanitized_mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp_repeat10",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp_repeat10',
path='./data/mbpp/sanitized-mbpp.jsonl',
num_repeats=10,
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
......
......@@ -3,24 +3,24 @@ 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_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 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 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: 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset,
abbr="mbpp",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp',
path='./data/mbpp/mbpp.jsonl',
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
eval_cfg=mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MBPPDataset_V2, MBPPPassKEvaluator
mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
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 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 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: 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset_V2,
abbr="mbpp_passk",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp_passk',
path='./data/mbpp/mbpp.jsonl',
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
eval_cfg=mbpp_eval_cfg,
......
......@@ -5,24 +5,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MBPPDataset_V2, MBPPPassKEvaluator
mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
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 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 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: 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"),
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'),
],
),
),
......@@ -30,13 +30,13 @@ mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
mbpp_datasets = [
dict(
type=MBPPDataset_V2,
abbr="mbpp_repeat10",
path="./data/mbpp/mbpp.jsonl",
abbr='mbpp_repeat10',
path='./data/mbpp/mbpp.jsonl',
num_repeats=10,
reader_cfg=mbpp_reader_cfg,
infer_cfg=mbpp_infer_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_list_2")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_list_2')
sanitized_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 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 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: 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ sanitized_mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp',
path='./data/mbpp/sanitized-mbpp.jsonl',
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
eval_cfg=sanitized_mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPPassKEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
sanitized_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 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 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: 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ sanitized_mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp_passk",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp_passk',
path='./data/mbpp/sanitized-mbpp.jsonl',
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
eval_cfg=sanitized_mbpp_eval_cfg,
......
......@@ -3,24 +3,24 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import SanitizedMBPPDataset, MBPPPassKEvaluator
sanitized_mbpp_reader_cfg = dict(input_columns=["text", "test_list"], output_column="test_column")
sanitized_mbpp_reader_cfg = dict(input_columns=['text', 'test_list'], output_column='test_column')
sanitized_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 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 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: 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"),
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'),
],
),
),
......@@ -28,13 +28,13 @@ sanitized_mbpp_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512),
)
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role="BOT")
sanitized_mbpp_eval_cfg = dict(evaluator=dict(type=MBPPPassKEvaluator), pred_role='BOT')
sanitized_mbpp_datasets = [
dict(
type=SanitizedMBPPDataset,
abbr="sanitized_mbpp_repeat10",
path="./data/mbpp/sanitized-mbpp.jsonl",
abbr='sanitized_mbpp_repeat10',
path='./data/mbpp/sanitized-mbpp.jsonl',
num_repeats=10,
reader_cfg=sanitized_mbpp_reader_cfg,
infer_cfg=sanitized_mbpp_infer_cfg,
......
......@@ -12,46 +12,46 @@ mbpp_infer_cfg = dict(
template=dict(
round=[
dict(
role="HUMAN",
role='HUMAN',
prompt=
"你是一名专业的 Python 程序员,你的任务是:编写一个函数,从给定的两个元组列表中查找相似的元素。 你的代码应该通过这些测试:\n\n assert similar_elements((3, 4, 5, 6),(5, 7, 4, 10)) == (4, 5)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert similar_elements((11, 12, 14, 13),(17, 15, 14, 13)) == (13, 14) \n"
'你是一名专业的 Python 程序员,你的任务是:编写一个函数,从给定的两个元组列表中查找相似的元素。 你的代码应该通过这些测试:\n\n assert similar_elements((3, 4, 5, 6),(5, 7, 4, 10)) == (4, 5)\n assert similar_elements((1, 2, 3, 4),(5, 4, 3, 7)) == (3, 4) \n assert similar_elements((11, 12, 14, 13),(17, 15, 14, 13)) == (13, 14) \n'
),
dict(
role="BOT",
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",
role='HUMAN',
prompt=
"你是一名专业的 Python 程序员,你的任务是:编写一个 Python 函数来识别一个整数是否不是素数。 你的代码应该通过这些测试:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert is_not_prime(35) == True \n"
'你是一名专业的 Python 程序员,你的任务是:编写一个 Python 函数来识别一个整数是否不是素数。 你的代码应该通过这些测试:\n\n assert is_not_prime(2) == False \n assert is_not_prime(10) == True \n assert is_not_prime(35) == True \n'
),
dict(
role="BOT",
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",
role='HUMAN',
prompt=
"你是一名专业的 Python 程序员,你的任务是:编写一个函数,使用堆队列算法从给定的数字列表中查找最大整数。 你的代码应该通过这些测试:\n\n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],3)==[85, 75, 65] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],5)==[85, 75, 65, 58, 35] \n"
'你是一名专业的 Python 程序员,你的任务是:编写一个函数,使用堆队列算法从给定的数字列表中查找最大整数。 你的代码应该通过这些测试:\n\n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],3)==[85, 75, 65] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],2)==[85, 75] \n assert heap_queue_largest( [25, 35, 22, 85, 14, 65, 75, 22, 58],5)==[85, 75, 65, 58, 35] \n'
),
dict(
role="BOT",
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",
role='HUMAN',
prompt=
"你是一名专业的 Python 程序员,你的任务是: {text} 你的代码应该通过这些测试:\n\n {test_list} \n"
'你是一名专业的 Python 程序员,你的任务是: {text} 你的代码应该通过这些测试:\n\n {test_list} \n'
),
dict(role="BOT", prompt="[BEGIN]\n"),
dict(role='BOT', prompt='[BEGIN]\n'),
], )),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role="BOT")
mbpp_eval_cfg = dict(evaluator=dict(type=MBPPEvaluator), pred_role='BOT')
mbpp_cn_datasets = [
dict(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment