Model reference · open weights
KURE is an open-weight embedding model from nlpai-lab, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
🔎 KURE-v1 Introducing Korea University Retrieval Embedding model, KURE-v1 It has shown remarkable performance in Korean text retrieval, speficially overwhelming most multilingual embedding models. To our knowledge, It is one of the best publicly opened Korean retrieval models. For details, visit the KURE repository Model Versions Model Description This is the model card of a 🤗 transformers model that has been pushed on the Hub. - Developed by: NLP&AI Lab - Language(s) (NLP): Korean, English - License: MIT - Finetuned from model: BAAI/bge-m3 Example code Install Dependencies First install the Sentence Transformers library: Python code Then you can load this model and run inference. Training Details Training Data KURE-v1 - Korean query-document-hardnegative(5) data - 2,000,000 examples Training Procedure - loss: Used CachedGISTEmbedLoss by sentence-transformers - batch size: 4096 - learning rate: 2e-05 - epochs: 1 Evaluation Metrics - Recall, Precision, NDCG, F1 Benchmark Datasets - Ko-StrategyQA: 한국어 ODQA multi-hop 검색 데이터셋 (StrategyQA 번역) - AutoRAGRetrieval: 금융, 공공, 의료, 법률, 커머스 5개 분야에 대해, pdf를 파싱하여 구성한 한국어 문서 검색 데이터셋 - MIRACLRetrieval): Wikipedia 기반의 한국어 문서 검색 데이터셋 - PublicHealthQA): 의료 및 공중보건 도메인에 대한 한국어 문서 검색 데이터셋 - BelebeleRetrieval): FLORES-200 기반의 한국어 문서 검색 데이터셋 - MrTidyRetrieval: Wikipedia 기반의 한국어 문서 검색 데이터셋 - MultiLongDocRetrieval: 다양한 도메인의 한국어 장문 검색 데이터셋 - XPQARetrieval: 다양한 도메인의 한국어 문서 검색 데이터셋 Results 아래는 모든 모델의, 모든 벤치마크 데이터셋에 대한 평균 결과입니다. 자세한 결과는 KURE Github에서 확인하실 수 있습니다. Top-k 1 Top-k 3 Top-k 5 Top-k 10 Citation If you find our paper or models helpful, please consider cite as follows:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nlpai-lab |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 568M |
| Context | 8,194 tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Based on | BAAI/bge-m3 |
| Released | 2024-12-18 |
| Popularity | 362k downloads / month |
| Likes | 93 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| KURE-v1 | 568M | BF16 | ~1.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys kure for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (kure below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kure","input":"text to embed"}'
Details
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore