Downloads · 30 days
29
63% of all-time downloads
Sophea-Nemo-Embedding
ayoubkirouane/Sophea-Nemo-Embedding
Sophea-Nemo-Embedding is a sentence similarity model from ayoubkirouane. 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 other.
<div style="display:flex;align-items:center;gap:18px;padding:16px 20px;margin-bottom:16px;border-radius:14px;background:linear-gradient(100deg,e8f5ec 0%,f7fbf8 62%);border:1px solid c6e7d1"<img alt="KIEFERSA" style="f…
All-time downloads
46
Public
Parameters
1.1B
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
At a glance
- Task
- Sentence Similarity
- Library
- sentence-transformers
- License
- other
- Model type
- ministral3
- Access
- Public
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026
- SHA
- bacc3c72
Base models
Model card
From the Hugging Face model README
<div style="display:flex;align-items:center;gap:18px;padding:16px 20px;margin-bottom:16px;border-radius:14px;background:linear-gradient(100deg,#e8f5ec 0%,#f7fbf8 62%);border:1px solid #c6e7d1"><img alt="KIEFERSA" style="flex:0 0 auto;height:58px;width:58px;border-radius:12px;object-fit:contain" src="data:image/webp;base64,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"/><div><div style="font-size:1.24rem;font-weight:700;color:#003713;line-height:1.2">Sophea-Nemo-Embedding</div><div style="font-size:.86rem;color:#3a5a47;margin-top:2px">Greek + English dense retriever — fine-tuned NVIDIA Nemotron-3-Embed-1B</div></div></div>
Sophea-Nemo-Embedding is a Greek + English dense retrieval embedder, fine-tuned from NVIDIA Nemotron-3-Embed-1B for Greek and English retrieval. It is the first stage of a two-stage Greek RAG stack; the matching second stage is Sophea-Nemo-Reranker.
- Creator: Kiefer SA
- Base model:
nvidia/Nemotron-3-Embed-1B-BF16(Ministral-3 backbone, bidirectional, mean pooling withinclude_prompt=true, 2048-d Matryoshka-sliceable, L2-normalized) - Languages: Greek + English
- Prompts:
query:on queries,passage:on documents (both sides prompted) - Training: full fine-tune, InfoNCE (in-batch + 7 hard negatives), 1 epoch, max-len 4096, bf16
Greek is out-of-distribution for the base. Nemotron-3-Embed lists 34 languages and Greek is not one of them — which is exactly why the base retrieves poorly on Greek and why this fine-tune exists.
Why it matters — base vs fine-tuned
On our held-out 5-domain Greek+English retrieval eval (cosine IR, query: /passage: prompts), the
fine-tune roughly 2.5×'s the base embedder's retrieval quality — on every domain.
Read. Mean nDCG@10 0.331 → 0.818 (+0.486), with the largest gains on the hardest domains (finance +0.53, medical +0.54). Recall@10 climbs from a mean 0.425 to 0.931 — i.e. the right passage is now almost always in the top-10.
Size comparison — vs base Qwen3-Embedding (off-the-shelf)
Same 5-domain retrieval eval, same corpus/prompts. Your fine-tuned 1B embedder beats the base Qwen3-Embedding-8B by a wide margin (nDCG@10):
<div style="overflow-x:auto"> <table style="width:100%;border-collapse:collapse;font-size:13px;font-variant-numeric:tabular-nums;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif"> <thead><tr> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:left;">model</th> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:center;">Val</th> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:center;">Energy</th> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:center;">Legal</th> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:center;">Finance</th> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:center;">Medical</th> <th style="padding:10px 8px;font-weight:500;border-bottom:2px solid #0a8043;color:#0a8043;font-size:14px;text-align:center;">Mean</th> </tr></thead><tbody> <tr><td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">Sophea-Nemo-Embedding (ours · 1B · fine-tuned)</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">0.875</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">0.794</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">0.950</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">0.722</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">0.747</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);font-weight:700;color:#0a8043;">0.818</td></tr> <tr><td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);">Qwen3-Embedding-8B (base, off-the-shelf)</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.740</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.580</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.910</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.490</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.602</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.664</td></tr> <tr><td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);">Qwen3-Embedding-4B (base, off-the-shelf)</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.738</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.579</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.919</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.501</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.586</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.665</td></tr> <tr><td style="padding:7px 8px;padding-left:20px;text-align:left;border-bottom:1px solid rgba(128,128,128,.15);">Qwen3-Embedding-0.6B (base, off-the-shelf)</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.658</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.509</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.863</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.426</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.467</td><td style="padding:7px 8px;text-align:center;border-bottom:1px solid rgba(128,128,128,.15);">0.585</td></tr> </tbody></table></div>Read. Mean nDCG@10 0.818 (ours, 1B) vs 0.664 (8B), 0.665 (4B), 0.585 (0.6B). Note the Qwen 8B ≈ 4B — scaling the off-the-shelf model barely helps on Greek, whereas a 1B fine-tuned on-domain wins by +0.153 over the 8×-larger model.
End-to-end two-stage pipeline
The two models are designed to run together: the embedder retrieves the top-50 candidates, the
reranker re-orders them. Measured end-to-end on the same 5-domain Greek+English eval (150 queries/set,
correct query:/passage: prompts):
Read. The full stack reaches mean nDCG@10 0.818 (Recall@10 0.927) — the
strongest configuration measured. The reranker adds the most where the embedder is weakest
(finance +0.061, legal +0.037), i.e. it sharpens precision on the hard
cases. On energy it slightly regresses (-0.022) and on val the gain is marginal,
because the embedder alone is already very strong there and leaves little headroom — for the easiest,
already-high-recall domains you can skip the rerank stage if latency matters.
Usage (sentence-transformers)
from sentence_transformers import SentenceTransformer
m = SentenceTransformer("KIEFERSA/Sophea-Nemo-Embedding")
q = m.encode(["Ποια είναι η πρωτεύουσα της Ελλάδας;"], prompt="query: ", normalize_embeddings=True)
d = m.encode(["Η Αθήνα είναι η πρωτεύουσα της Ελλάδας."], prompt="passage: ", normalize_embeddings=True)
print((q @ d.T)) # cosine similarity
Both sides must be prompted (query: / passage: ) — the base uses include_prompt=true, so
dropping the prefix is a distribution mismatch. Embeddings are L2-normalized (use cosine / dot).
Serving with vLLM
vllm serve KIEFERSA/Sophea-Nemo-Embedding --runner pooling
Exposes an OpenAI-compatible /v1/embeddings endpoint. vLLM does not auto-apply the model's ST
prompts, so prepend them client-side — query: on queries, passage: on documents:
from openai import OpenAI
c = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
name = "KIEFERSA/Sophea-Nemo-Embedding"
q = c.embeddings.create(model=name, input=["query: Ποια είναι η πρωτεύουσα της Ελλάδας;"]).data[0].embedding
d = c.embeddings.create(model=name, input=["passage: Η Αθήνα είναι η πρωτεύουσα της Ελλάδας."]).data[0].embedding
License
Fine-tune of nvidia/Nemotron-3-Embed-1B-BF16 — governed by OpenMDW-1.1 (base Ministral-3 is
Apache-2.0); commercial use permitted under those terms. Review the base model's license before use.
- Task
- Sentence Similarity
- Library
- sentence-transformers
- Type
- ministral3
- License
- other
- Languages
- el, en
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026