Skip to content

Commit

Permalink
docs: Add MTEB(code) dataset (#1237)
Browse files Browse the repository at this point in the history
* docs: Add MTEB(code) dataset

* Fix linting
  • Loading branch information
john-b-yang authored Sep 24, 2024
1 parent dddf5c2 commit f808863
Show file tree
Hide file tree
Showing 3 changed files with 41 additions and 1 deletion.
2 changes: 1 addition & 1 deletion docs/mmteb/points.md
Original file line number Diff line number Diff line change
Expand Up @@ -119,4 +119,4 @@ Please also add your first name and last name are as you want them to appear in
| mrshu | Marek | Suppa | [email protected] | ~Marek_Suppa1 | Comenius University in Bratislava && Cisco Systems |
| swj0419 | Weijia | Shi | [email protected] | ~Weijia_Shi1 | University of Washington |
| xiamengzhou | Mengzhou | Xia | [email protected] | ~Mengzhou_Xia1 | Princeton University |
| john-b-yang | John | Yang | | ~John_Yang3 | Princeton University |
| john-b-yang | John | Yang | [email protected] | ~John_Yang3 | Stanford University |
1 change: 1 addition & 0 deletions docs/mmteb/points/1237.jsonl
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"GitHub": "john-b-yang", "Paper writing": 20}
39 changes: 39 additions & 0 deletions mteb/benchmarks/benchmarks.py
Original file line number Diff line number Diff line change
Expand Up @@ -505,3 +505,42 @@ def __getitem__(self, index):
year={2024}
}""",
)

MTEB_code = Benchmark(
name="MTEB(code)",
tasks=get_tasks(
tasks=[
# Retrieval
"AppsRetrieval",
"CodeEditSearchRetrieval",
"CodeFeedbackMT",
"CodeFeedbackST",
"CodeSearchNetCCRetrieval",
"CodeSearchNetRetrieval",
"CodeTransOceanContest",
"CodeTransOceanDL",
"CosQA",
"COIRCodeSearchNetRetrieval",
"StackOverflowQA",
"SyntheticText2SQL",
],
languages=[
"c",
"c++",
"go",
"java",
"javascript",
"php",
"python",
"ruby",
"rust",
"scala",
"shell",
"swift",
"typescript",
],
),
description="Main code benchmarks from MTEB",
reference=None,
citation=None,
)

0 comments on commit f808863

Please sign in to comment.