51 lines
2.1 KiB
Python
51 lines
2.1 KiB
Python
"""SWE-bench Verified (official source: princeton-nlp/SWE-bench_Verified)."""
|
|
|
|
from ..sample import Sample, SandboxSpec
|
|
from ..registry import register_dataset
|
|
from ..spec import DatasetSpec
|
|
|
|
|
|
@register_dataset(
|
|
DatasetSpec(
|
|
name='swe_bench_verified',
|
|
source='princeton-nlp/SWE-bench_Verified', # official: https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified
|
|
split='test',
|
|
gen_config={'temperature': 0.0, 'max_tokens': 32768},
|
|
task_type='agent',
|
|
tags=['code', 'agent', 'swe'],
|
|
requires=['docker'],
|
|
description='SWE-bench Verified; per-instance docker image carried in Sample.sandbox.',
|
|
)
|
|
)
|
|
def swe_bench_verified():
|
|
def to_sample(record: dict) -> Sample:
|
|
instance_id = record['instance_id']
|
|
# image naming: local swebench/ set uses {repo}_1776_{repo}-{num}; the
|
|
# newer official layout is sweb.eval.x86_64.{repo}__{repo}-{num}
|
|
# OFFICIAL docker layout: repo-level BASE images
|
|
# (swebench/sweb.eval.x86_64.{repo}) -- per-instance images are
|
|
# NEVER published; the harness builds them on top of the base
|
|
_repo = instance_id.rsplit('-', 1)[0]
|
|
img = f'swebench/sweb.eval.x86_64.{_repo}:latest'
|
|
if '__' in instance_id:
|
|
repo, num = instance_id.rsplit('-', 1)
|
|
r = repo.split('__')[0]
|
|
img = f'swebench/sweb.eval.x86_64.{r}_1776_{r.split("__")[-1]}-{num}'
|
|
return Sample(
|
|
input=record['problem_statement'],
|
|
target=record['patch'], # gold patch (for oracle/oracle-check only)
|
|
sandbox=SandboxSpec(image=img),
|
|
metadata={
|
|
'instance_id': instance_id,
|
|
'repo': record['repo'],
|
|
'base_commit': record['base_commit'],
|
|
'test_patch': record['test_patch'],
|
|
'FAIL_TO_PASS': record['FAIL_TO_PASS'],
|
|
'PASS_TO_PASS': record['PASS_TO_PASS'],
|
|
'environment_setup_commit': record.get('environment_setup_commit'),
|
|
'difficulty': record.get('difficulty'),
|
|
},
|
|
)
|
|
|
|
return to_sample
|