mirror of
https://github.com/FoundationAgents/MetaGPT.git
synced 2026-05-01 20:03:28 +02:00
Update
This commit is contained in:
didi
parent
7fa68d5649
commit
8a241054c7
8 changed files with 301 additions and 120 deletions
96
test.ipynb
96
test.ipynb
|
|
@ -2,26 +2,14 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Usage\n",
|
||||
"\n",
|
||||
"human_eval_example = \"\"\"\n",
|
||||
"from typing import List\\n\\n\\ndef has_close_elements(numbers: List[float], threshold: float) -> bool:\\n \\\"\\\"\\\" Check if in given list of numbers, are any two numbers closer to each other than\\n given threshold.\\n >>> has_close_elements([1.0, 2.0, 3.0], 0.5)\\n False\\n >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)\\n True\\n \\\"\\\"\\\"\\n\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"problem = \"\"\"\n",
|
||||
"Human: Write a function that takes a list of numbers and returns the sum of the numbers at even indices.\n",
|
||||
"\n",
|
||||
"Function Signature:\n",
|
||||
"def sum_even_indices(numbers: List[int]) -> int:\n",
|
||||
"\n",
|
||||
"Example:\n",
|
||||
">>> sum_even_indices([1, 2, 3, 4, 5])\n",
|
||||
"9 # 1 + 3 + 5 = 9\n",
|
||||
"\"\"\""
|
||||
"# TODO 帮助我写一个代码，找出这种结构中，都出现的id与并不是都出现的id，以及第一，二，三批单独出现的id，\n",
|
||||
"test_1 = [{'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/4'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/8'}, {'task_id': 'HumanEval/10'}, {'task_id': 'HumanEval/11'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/17'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/25'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/41'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/77'}, {'task_id': 'HumanEval/81'}, {'task_id': 'HumanEval/90'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/93'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/97'}, {'task_id': 'HumanEval/98'}, {'task_id': 'HumanEval/99'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/115'}, {'task_id': 'HumanEval/118'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/121'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/133'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/138'}, {'task_id': 'HumanEval/139'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/154'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/163'}]\n",
|
||||
"test_2 = [{'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/4'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/8'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/10'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/17'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/25'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/33'}, {'task_id': 'HumanEval/41'}, {'task_id': 'HumanEval/64'}, {'task_id': 'HumanEval/65'}, {'task_id': 'HumanEval/67'}, {'task_id': 'HumanEval/70'}, {'task_id': 'HumanEval/74'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/81'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/85'}, {'task_id': 'HumanEval/88'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/90'}, {'task_id': 'HumanEval/93'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/98'}, {'task_id': 'HumanEval/99'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/115'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/149'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/163'}]\n",
|
||||
"test_3 = [{'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/4'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/8'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/10'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/17'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/25'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/33'}, {'task_id': 'HumanEval/65'}, {'task_id': 'HumanEval/67'}, {'task_id': 'HumanEval/70'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/76'}, {'task_id': 'HumanEval/77'}, {'task_id': 'HumanEval/81'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/93'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/101'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/115'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/121'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/138'}, {'task_id': 'HumanEval/139'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/163'}]"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -33,39 +21,69 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'code': 'from typing import List\\n\\ndef has_close_elements(numbers: List[float], threshold: float) -> bool:\\n \"\"\" Check if in given list of numbers, are any two numbers closer to each other than\\n given threshold.\\n >>> has_close_elements([1.0, 2.0, 3.0], 0.5)\\n False\\n >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)\\n True\\n \"\"\"\\n numbers_sorted = sorted(numbers)\\n for i in range(len(numbers_sorted) - 1):\\n if abs(numbers_sorted[i] - numbers_sorted[i + 1]) < threshold:\\n return True\\n return False'}\n",
|
||||
"{'result': True}\n"
|
||||
"Common IDs: length:41 {'HumanEval/102', 'HumanEval/5', 'HumanEval/77', 'HumanEval/134', 'HumanEval/75', 'HumanEval/28', 'HumanEval/110', 'HumanEval/108', 'HumanEval/126', 'HumanEval/145', 'HumanEval/26', 'HumanEval/21', 'HumanEval/135', 'HumanEval/163', 'HumanEval/6', 'HumanEval/132', 'HumanEval/1', 'HumanEval/125', 'HumanEval/129', 'HumanEval/159', 'HumanEval/32', 'HumanEval/111', 'HumanEval/142', 'HumanEval/140', 'HumanEval/12', 'HumanEval/100', 'HumanEval/120', 'HumanEval/160', 'HumanEval/84', 'HumanEval/119', 'HumanEval/124', 'HumanEval/20', 'HumanEval/137', 'HumanEval/127', 'HumanEval/7', 'HumanEval/14', 'HumanEval/0', 'HumanEval/116', 'HumanEval/113', 'HumanEval/130', 'HumanEval/91'}\n",
|
||||
"Not Common IDs: {'HumanEval/37', 'HumanEval/46', 'HumanEval/88', 'HumanEval/8', 'HumanEval/29', 'HumanEval/123', 'HumanEval/118', 'HumanEval/41', 'HumanEval/122', 'HumanEval/49', 'HumanEval/64', 'HumanEval/131', 'HumanEval/114', 'HumanEval/22', 'HumanEval/73', 'HumanEval/76', 'HumanEval/94', 'HumanEval/71', 'HumanEval/39', 'HumanEval/148', 'HumanEval/109', 'HumanEval/121', 'HumanEval/133', 'HumanEval/155', 'HumanEval/68', 'HumanEval/65', 'HumanEval/99', 'HumanEval/80', 'HumanEval/144', 'HumanEval/93', 'HumanEval/98', 'HumanEval/16', 'HumanEval/33', 'HumanEval/156', 'HumanEval/10', 'HumanEval/136', 'HumanEval/153', 'HumanEval/3', 'HumanEval/90', 'HumanEval/154', 'HumanEval/139', 'HumanEval/17', 'HumanEval/87', 'HumanEval/19', 'HumanEval/138', 'HumanEval/89', 'HumanEval/9', 'HumanEval/69', 'HumanEval/25', 'HumanEval/54', 'HumanEval/63'}\n",
|
||||
"Unique to test_1: {'HumanEval/46', 'HumanEval/123', 'HumanEval/71', 'HumanEval/3', 'HumanEval/54', 'HumanEval/109'}\n",
|
||||
"Unique to test_2: {'HumanEval/121', 'HumanEval/88', 'HumanEval/133', 'HumanEval/139', 'HumanEval/8', 'HumanEval/65', 'HumanEval/114', 'HumanEval/144', 'HumanEval/73', 'HumanEval/69', 'HumanEval/16', 'HumanEval/90'}\n",
|
||||
"Unique to test_3: {'HumanEval/155', 'HumanEval/37', 'HumanEval/93', 'HumanEval/98', 'HumanEval/153', 'HumanEval/25', 'HumanEval/63', 'HumanEval/19', 'HumanEval/33', 'HumanEval/89', 'HumanEval/148', 'HumanEval/39', 'HumanEval/136', 'HumanEval/49'}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'code': 'from typing import List\\n\\ndef has_close_elements(numbers: List[float], threshold: float) -> bool:\\n \"\"\" Check if in given list of numbers, are any two numbers closer to each other than\\n given threshold.\\n >>> has_close_elements([1.0, 2.0, 3.0], 0.5)\\n False\\n >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)\\n True\\n \"\"\"\\n numbers_sorted = sorted(numbers)\\n for i in range(len(numbers_sorted) - 1):\\n if abs(numbers_sorted[i] - numbers_sorted[i + 1]) < threshold:\\n return True\\n return False'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Test\n",
|
||||
"def extract_ids(test_list):\n",
|
||||
" return set(item['task_id'] for item in test_list)\n",
|
||||
"\n",
|
||||
"from examples.ags.demo.graph import HumanEvalGraph\n",
|
||||
"solver = HumanEvalGraph(name=\"solver\", llm='gpt-4-turbo', criteria='correctness, efficiency, readability')\n",
|
||||
"result = solver(human_eval_example)\n",
|
||||
"result"
|
||||
"def compare_ids(test_1, test_2, test_3):\n",
|
||||
" ids_1 = extract_ids(test_1)\n",
|
||||
" ids_2 = extract_ids(test_2)\n",
|
||||
" ids_3 = extract_ids(test_3)\n",
|
||||
"\n",
|
||||
" common_ids = ids_1 & ids_2 & ids_3\n",
|
||||
" all_ids = ids_1 | ids_2 | ids_3\n",
|
||||
" not_common_ids = all_ids - common_ids\n",
|
||||
"\n",
|
||||
" unique_1 = ids_1 - (ids_2 | ids_3)\n",
|
||||
" unique_2 = ids_2 - (ids_1 | ids_3)\n",
|
||||
" unique_3 = ids_3 - (ids_1 | ids_2)\n",
|
||||
"\n",
|
||||
" return {\n",
|
||||
" 'common_ids': common_ids,\n",
|
||||
" 'not_common_ids': not_common_ids,\n",
|
||||
" 'unique_1': unique_1,\n",
|
||||
" 'unique_2': unique_2,\n",
|
||||
" 'unique_3': unique_3\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
"# Assuming test_1, test_2, and test_3 are defined as in your example\n",
|
||||
"result = compare_ids(test_1, test_2, test_3)\n",
|
||||
"\n",
|
||||
"print(\"Common IDs:\",f\"length:{len(result['common_ids'])}\", result['common_ids'])\n",
|
||||
"print(\"Not Common IDs:\",result['not_common_ids'])\n",
|
||||
"print(\"Unique to test_1:\", result['unique_1'])\n",
|
||||
"print(\"Unique to test_2:\", result['unique_2'])\n",
|
||||
"print(\"Unique to test_3:\", result['unique_3'])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# TODO\n",
|
||||
"# 1. 改成MG\n",
|
||||
"# 2. 添加HumanEval"
|
||||
"test_1 = [{'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/8'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/10'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/17'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/36'}, {'task_id': 'HumanEval/37'}, {'task_id': 'HumanEval/41'}, {'task_id': 'HumanEval/62'}, {'task_id': 'HumanEval/65'}, {'task_id': 'HumanEval/64'}, {'task_id': 'HumanEval/77'}, {'task_id': 'HumanEval/81'}, {'task_id': 'HumanEval/80'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/87'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/93'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/98'}, {'task_id': 'HumanEval/99'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/106'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/109'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/114'}, {'task_id': 'HumanEval/118'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/133'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/138'}, {'task_id': 'HumanEval/139'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/148'}, {'task_id': 'HumanEval/154'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/160'}, {'task_id': 'HumanEval/163'}]\n",
|
||||
"test_2 = [{'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/54'}, {'task_id': 'HumanEval/64'}, {'task_id': 'HumanEval/70'}, {'task_id': 'HumanEval/73'}, {'task_id': 'HumanEval/74'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/82'}, {'task_id': 'HumanEval/81'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/83'}, {'task_id': 'HumanEval/88'}, {'task_id': 'HumanEval/89'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/101'}, {'task_id': 'HumanEval/102'}, {'task_id': 'HumanEval/106'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/109'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/114'}, {'task_id': 'HumanEval/115'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/118'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/131'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/133'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/144'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/155'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/160'}, {'task_id': 'HumanEval/163'}]\n",
|
||||
"test_3 = [{'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/19'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/36'}, {'task_id': 'HumanEval/39'}, {'task_id': 'HumanEval/41'}, {'task_id': 'HumanEval/43'}, {'task_id': 'HumanEval/64'}, {'task_id': 'HumanEval/65'}, {'task_id': 'HumanEval/69'}, {'task_id': 'HumanEval/80'}, {'task_id': 'HumanEval/83'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/87'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/93'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/99'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/101'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/109'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/118'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/121'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/116'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/138'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/154'}, {'task_id': 'HumanEval/160'}, {'task_id': 'HumanEval/163'}]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"test_1 = [{'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/3'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/17'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/46'}, {'task_id': 'HumanEval/54'}, {'task_id': 'HumanEval/64'}, {'task_id': 'HumanEval/68'}, {'task_id': 'HumanEval/71'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/76'}, {'task_id': 'HumanEval/77'}, {'task_id': 'HumanEval/80'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/87'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/102'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/109'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/116'}, {'task_id': 'HumanEval/118'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/123'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/131'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/138'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/156'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/160'}, {'task_id': 'HumanEval/163'}]\n",
|
||||
"test_2 = [{'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/8'}, {'task_id': 'HumanEval/9'}, {'task_id': 'HumanEval/10'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/16'}, {'task_id': 'HumanEval/17'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/41'}, {'task_id': 'HumanEval/65'}, {'task_id': 'HumanEval/69'}, {'task_id': 'HumanEval/73'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/77'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/88'}, {'task_id': 'HumanEval/90'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/99'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/102'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/114'}, {'task_id': 'HumanEval/116'}, {'task_id': 'HumanEval/118'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/121'}, {'task_id': 'HumanEval/122'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/133'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/138'}, {'task_id': 'HumanEval/139'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/144'}, {'task_id': 'HumanEval/154'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/160'}, {'task_id': 'HumanEval/163'}]\n",
|
||||
"test_3 = [{'task_id': 'HumanEval/0'}, {'task_id': 'HumanEval/1'}, {'task_id': 'HumanEval/5'}, {'task_id': 'HumanEval/6'}, {'task_id': 'HumanEval/7'}, {'task_id': 'HumanEval/10'}, {'task_id': 'HumanEval/12'}, {'task_id': 'HumanEval/14'}, {'task_id': 'HumanEval/20'}, {'task_id': 'HumanEval/19'}, {'task_id': 'HumanEval/22'}, {'task_id': 'HumanEval/21'}, {'task_id': 'HumanEval/25'}, {'task_id': 'HumanEval/26'}, {'task_id': 'HumanEval/28'}, {'task_id': 'HumanEval/29'}, {'task_id': 'HumanEval/32'}, {'task_id': 'HumanEval/33'}, {'task_id': 'HumanEval/37'}, {'task_id': 'HumanEval/39'}, {'task_id': 'HumanEval/41'}, {'task_id': 'HumanEval/49'}, {'task_id': 'HumanEval/63'}, {'task_id': 'HumanEval/64'}, {'task_id': 'HumanEval/68'}, {'task_id': 'HumanEval/75'}, {'task_id': 'HumanEval/76'}, {'task_id': 'HumanEval/77'}, {'task_id': 'HumanEval/80'}, {'task_id': 'HumanEval/84'}, {'task_id': 'HumanEval/87'}, {'task_id': 'HumanEval/89'}, {'task_id': 'HumanEval/91'}, {'task_id': 'HumanEval/93'}, {'task_id': 'HumanEval/94'}, {'task_id': 'HumanEval/98'}, {'task_id': 'HumanEval/100'}, {'task_id': 'HumanEval/99'}, {'task_id': 'HumanEval/102'}, {'task_id': 'HumanEval/108'}, {'task_id': 'HumanEval/110'}, {'task_id': 'HumanEval/111'}, {'task_id': 'HumanEval/113'}, {'task_id': 'HumanEval/116'}, {'task_id': 'HumanEval/120'}, {'task_id': 'HumanEval/119'}, {'task_id': 'HumanEval/124'}, {'task_id': 'HumanEval/126'}, {'task_id': 'HumanEval/125'}, {'task_id': 'HumanEval/127'}, {'task_id': 'HumanEval/129'}, {'task_id': 'HumanEval/131'}, {'task_id': 'HumanEval/132'}, {'task_id': 'HumanEval/130'}, {'task_id': 'HumanEval/134'}, {'task_id': 'HumanEval/135'}, {'task_id': 'HumanEval/137'}, {'task_id': 'HumanEval/136'}, {'task_id': 'HumanEval/140'}, {'task_id': 'HumanEval/142'}, {'task_id': 'HumanEval/145'}, {'task_id': 'HumanEval/148'}, {'task_id': 'HumanEval/153'}, {'task_id': 'HumanEval/154'}, {'task_id': 'HumanEval/155'}, {'task_id': 'HumanEval/156'}, {'task_id': 'HumanEval/159'}, {'task_id': 'HumanEval/160'}, {'task_id': 'HumanEval/163'}]"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -85,7 +103,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.7"
|
||||
"version": "3.9.19"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue