Model reference · open weights

Vela-1.0-Encoder-Embedding

Available as managed deployment Embeddings llm-semantic-router Embeddings 1 variants 672 dl/mo

Vela-1.0-Encoder-Embedding is an open-weight embedding model from llm-semantic-router. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byllm-semantic-router
TypeEmbedding models
TaskEmbeddings
Parameters (lead)307M
Context32k tokens
Runs withsentence-transformers
Based onllm-semantic-router/Vela-1.0-Encoder-307M
Released2026-09-12
Popularity672 downloads / month
LicenceOpen weights

About

What Vela-1.0-Encoder-Embedding is

Connect requests with the right context. Vela Embedding powers multilingual semantic matching, retrieval, and memory in your router.

307M parameters · 32K context · Multilingual

Read the full model card

Evaluation

Compared with the original mmBERT Embedding. Scores are ×100; higher is better.

Selected tasks from MTEB 2.21.0:

TaskOriginal mmBERTVela
Banking7772.2673.76
MASSIVE · English63.5168.24
MASSIVE · Chinese61.4166.06
DuRetrieval62.4762.18
NFCorpus26.3826.11
SciFact46.8147.64
PAWS-X · English62.9871.80
PAWS-X · Chinese59.2962.91
STS-B · Chinese75.0074.61
STS-B · English80.3881.06
CLS Clustering34.2034.55
Twenty Newsgroups Clustering38.0539.79
Tatoeba · Chinese–English89.1388.72

Long-document retrieval:

EvaluationMetricOriginal mmBERTVela
SummScreenFD · 336 queriesnDCG@1076.9988.47

Both models use 22 layers, 768 dimensions and FP32. The MTEB rows use each task's standard main metric; SummScreenFD uses its validation split.

These results describe the listed tasks, not a full MTEB score or ranking.

Quick start

Install sentence-transformers. Use a ROCm-enabled PyTorch build for AMD GPUs.

import torch
from sentence_transformers import SentenceTransformer

model_id = "llm-semantic-router/Vela-1.0-Encoder-307M-Embedding"
device = "cuda" if torch.cuda.is_available() else "cpu"
model = SentenceTransformer(model_id, device=device)
vectors = model.encode([
    "The library opens in the morning.",
    "图书馆早上开门。",
])
print(vectors.shape)  # (2, 768)

The default returns 768-dimensional unit vectors. The 32,768-token input limit includes special tokens.

Explore the Vela collection

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys vela-1-0-encoder-embedding for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vela-1-0-encoder-embedding 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":"vela-1-0-encoder-embedding","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms