github/OpenHands
1
1
Fork 0
mirror of https://github.com/All-Hands-AI/OpenHands.git synced 2026-01-09 14:57:59 -05:00
Code Issues Packages Projects Releases Wiki Activity

[eval] SWE-Gym Integration (#6651)

Browse Source 
Co-authored-by: Robert Brennan <accounts@rbren.io>
Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
Co-authored-by: Graham Neubig <neubig@gmail.com>
This commit is contained in:
Xingyao Wang
2025-03-05 15:15:02 -05:00
committed by GitHub
parent bbf40c6576
commit 9f720a9d69
10 changed files with 638 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
poetry.lock generated
View File

@@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
# This file is automatically @generated by Poetry 2.0.0 and should not be changed by hand.
[[package]]
name = "aiohappyeyeballs"
@@ -8938,7 +8938,7 @@ files = [
[package.dependencies]
greenlet = [
{version = "!=0.4.17", optional = true, markers = "python_version < \"3.14\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\") or extra == \"asyncio\""},
{version = "!=0.4.17", markers = "python_version < \"3.14\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\")"},
{version = "!=0.4.17", optional = true, markers = "python_version < \"3.14\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\") or extra == \"asyncio\""},
]
typing-extensions = ">=4.6.0"
@@ -9109,14 +9109,14 @@ files = [
[[package]]
name = "swebench"
version = "3.0.13"
version = "3.0.15"
description = "The official SWE-bench package - a benchmark for evaluating LMs on software engineering"
optional = false
python-versions = ">=3.8"
groups = ["evaluation"]
files = [
{file = "swebench-3.0.13-py3-none-any.whl", hash = "sha256:0949e0a7269fcebb287dd951d14c049bd8189c7740fc4878354dbec756531c0f"},
{file = "swebench-3.0.13.tar.gz", hash = "sha256:d1cce406d0674cb1f3ca7da90089644d1ded3649c98f239a5a7ef4829d2f7c58"},
{file = "swebench-3.0.15-py3-none-any.whl", hash = "sha256:dd694356f9c155a55d3d2e113fe58446f7385eea0574230af5e2504426f8b85b"},
{file = "swebench-3.0.15.tar.gz", hash = "sha256:24e734fbcce34082665a25719075e6899382b7135103dd8c6cc09a6e23789101"},
]
[package.dependencies]
@@ -9139,6 +9139,39 @@ unidiff = "*"
inference = ["anthropic", "flash_attn", "jedi", "openai", "peft", "protobuf", "sentencepiece", "tiktoken", "torch", "transformers", "triton"]
test = ["pytest", "pytest-cov"]
[[package]]
name = "swegym"
version = "2.0.13"
description = "Fork of SWE-bench package - a benchmark for evaluating LMs on software engineering"
optional = false
python-versions = ">=3.8"
groups = ["evaluation"]
files = []
develop = false
[package.dependencies]
beautifulsoup4 = "*"
chardet = "*"
datasets = "*"
docker = "*"
ghapi = "*"
GitPython = "*"
pre-commit = "*"
python-dotenv = "*"
requests = "*"
rich = "*"
tqdm = "*"
unidiff = "*"
[package.extras]
inference = ["anthropic", "flash_attn", "jedi", "openai", "peft", "protobuf", "sentencepiece", "tenacity", "tiktoken", "torch", "transformers", "triton"]
[package.source]
type = "git"
url = "https://github.com/SWE-Gym/SWE-Bench-Package.git"
reference = "HEAD"
resolved_reference = "16dd480cce9b27bf111a362d280881c6def5d2a7"
[[package]]
name = "sympy"
version = "1.13.1"
@@ -10855,4 +10888,4 @@ testing = ["coverage[toml]", "zope.event", "zope.testing"]
[metadata]
lock-version = "2.1"
python-versions = "^3.12"
content-hash = "83da0b681253a79417c9842862cdd102c1ab6e8770d9dd9e0c42bc7994be2cd0"
content-hash = "c3f32c54606e5f313d9a909625f77cc3d575bf951e986633bcecd94520f36450"