Downloads · 30 days
18
47% of all-time downloads
kenga-embed-z
GermannM/kenga-embed-z
kenga-embed-z is a sentence similarity model from GermannM. Use it when you need a score for how close two texts are. It is set up for pytorch. The card lists the license as mit.
Older non-instruct Z-Embed, seq 96. Best handmade-holdout file we still have for Z (12/12 EN, 11/12 RU).
All-time downloads
38
Public
Repo size
168 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin168 MB · 100%
At a glance
- Task
- Sentence Similarity
- Library
- pytorch
- License
- mit
- Model type
- kenga-embed
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- bc7dd2a3
Model card
From the Hugging Face model README
kenga-embed-z
Older non-instruct Z-Embed, seq 96. Best handmade-holdout file we still have for Z (12/12 EN, 11/12 RU).
Do not apply the Giga instruct prefix to this checkpoint. Encode raw UTF-8 bytes.
from modeling_kenga_embed import KengaEmbed
m = KengaEmbed.from_pretrained("GermannM/kenga-embed-z")
# instruct=false in config
q = m.encode_queries(["Where is the capital of Russia?"]) # raw
d = m.encode_documents(["Moscow is the capital of Russia."])
Holdout (not ruMTEB): EN 1.000, RU 0.917, miss = Russian H2O.
RuSTS on this file (same weights, 2026-09-02, no instruct): 0.3723.
Later Z last weights are instruct+seq160 and currently lose the holdout if you mix templates. This upload is the frozen best.
- Task
- Sentence Similarity
- Library
- pytorch
- Type
- kenga-embed
- License
- mit
- Languages
- ru, en
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026