Downloads · 30 days
45
13% of all-time downloads
UlkuTuncerKucuktas/bge-m3-vistalab
bge-m3-vistalab is a sentence similarity model from UlkuTuncerKucuktas. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as mit.
Turkish embedding model fine-tuned from BAAI/bge-m3 on the VistalabBelirtecSyntheticDataset, a grounded synthetic Turkish corpus (legal + retrieval + STS + classification), using LoRA (r=32) with CachedGISTEmbedLoss a…
Downloads · 30 days
45
13% of all-time downloads
All-time downloads
347
Public
Parameters
568M
2.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.3 GB · 99%
From the Hugging Face model README
Turkish embedding model fine-tuned from BAAI/bge-m3 on the VistalabBelirtecSyntheticDataset, a grounded synthetic Turkish corpus (legal + retrieval + STS + classification), using LoRA (r=32) with CachedGISTEmbedLoss and Matryoshka representation learning (dims 1024, 256).
| Metric | Score |
|---|---|
| Legal (Contracts/Regulation/Caselaw avg) | 54.51 |
| MTEB Turkish (Mean TaskType) | 64.50 |
The model targets Turkish legal retrieval; the legal score reflects performance on Turkish contract, regulation, and case-law retrieval tasks.
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("UlkuTuncerKucuktas/bge-m3-vistalab")
emb = model.encode(["Türkçe bir cümle", "başka bir cümle"])