Commit History
2 days ago
-
HTML result tables, KURE rows in crimson
Verified signature04fb87d -
Show usage unfolded, fold the per-dataset tables
Verified signature63e39d7 -
Add API usage
Verified signatureba5d290
9 days ago
-
Update evaluation: PublicHealthQA/Belebele re-evaluated on corrected BM25 pools
Verified signature- PublicHealthQA and BelebeleRetrieval were scored against another query's BM25 candidates (the benchmark's mteb 1.x pools used per-process query ids); both are re-evaluated for every model, Belebele on its kor_Hang-kor_Hang subset. - Tables, key numbers and the figure updated; KURE-Reranker models drawn as stars. - Model weights are unchanged.f3b3eff
20 days ago
-
Update evaluation: official Qwen3-Reranker and KaLM-Reranker-V1-Large-R2 added, seq-cls variants and ettin removed (#3)
- Update evaluation: official Qwen3-Reranker and KaLM-Reranker-V1-Large-R2 added, seq-cls variants and ettin removed (c800441c6654fd6eebda9a83772e5af0a81d11c0)c32a78a
21 days ago
-
Use full KURE-Reranker names in the figure and fix a missing space in the PPS note (#2)
- Use full KURE-Reranker names in the figure and fix a missing space in the PPS note (f5a17034eddd6e745548308f871bff4f562db435) - Align the figure legend with the x=1000 tick (092f4039ed1244333cd8eeb140d93242b2dfb957) - Move the figure legend slightly left of the x=1000 tick (725a83c4c4d440f9ab6831ad2abe0f9bfe581dfa) Co-authored-by: Youngjoon Jang <yjoonjang@users.noreply.huggingface.co>3529662 -
Update model card with the current MTEB-ko-retrieval benchmark results (#1)
- Update model card with the current MTEB-ko-retrieval benchmark results (7d9e2ee042b33fd8fad3bda783557af1d05ab617) Co-authored-by: Youngjoon Jang <yjoonjang@users.noreply.huggingface.co>d4e648c
-
init
Verified signaturea31c5eb -
init
Verified signature3b8da88 -
init
Verified signatureab1e525