Views
No views yet
trmteb/turkish-embedding-model. Same weights (mean pooling, 768-d, L2-normalized),
converted with mlx-embeddings; verified at parity with the PyTorch source
(per-text cosine 1.00000; identical R@1/MRR).max_seq_length 5121import numpy as np, mlx_embeddings
2model, tok = mlx_embeddings.load("<this-repo-or-path>")
3o = mlx_embeddings.generate(model, tok, ["Örnek başlık.", "İkinci haber."])
4E = np.array(o.text_embeds) # already L2-normalized; cosine == dot productmlx>=0.30, mlx-embeddings>=0.1.0.dbmdz/bert-base-turkish-uncased, MIT).trmteb/turkish-embedding-model — no license is declared
upstream (as of 2026-07-03 the source model card states none); attribution retained.dbmdz/bert-base-turkish-uncased (BERTurk) — MIT. Retain
BERTurk's copyright and permission notice (see its model card).trmteb/turkish-embedding-model itself declares no license, so the MIT terms above
inherit from the BERTurk root and cover this fine-tune's contribution; confirm the
intermediate model's terms with its author before commercial redistribution.1@article{10.1007/s10579-021-09568-y,
2 year = {2022},
3 title = {{Abstractive text summarization and new large-scale datasets for agglutinative languages Turkish and Hungarian}},
4 author = {Baykara, Batuhan and Güngör, Tunga},
5 journal = {Language Resources and Evaluation},
6 issn = {1574-020X},
7 doi = {10.1007/s10579-021-09568-y},
8 pages = {1--35}
9}