Model reference · open weights

Vietnamese_Embedding

Vietnamese_Embedding is an open-weight embedding model from AITeamVN, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings AITeamVN 1 variants 31k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Vietnamese_Embedding is

Model Card: VietnameseEmbeddingv2 VietnameseEmbeddingv2 is an embedding model fine-tuned from the BGE-M3 model (https://huggingface.co/BAAI/bge-reranker-v2-m3) to enhance retrieval capabilities for Vietnamese. The model was trained on approximately 1,100,000 triplets of queries, positive documents, and negative documents for Vietnamese. The model was trained with a maximum sequence length of 2304 (256 for query and 2048 for passages). Model Details Model Description - Model Type: Sentence Transformer - Base model: BAAI/bge-m3 - Maximum Sequence Length: 2048 tokens - Output Dimensionality: 1024 dimensions - Similarity Function: Dot product Similarity - Language: Vietnamese - Licence: Apache 2.0 Usage Evaluation: - Dataset: Entire training dataset of Legal Zalo 2021. Our model was not trained on this dataset. VietnameseReranker and VietnameseEmbeddingv2 was trained on 1,100,000 triplets. Although the score on the legal domain drops a bit on VietnameseEmbedding (Phase 2), since this phase data is much larger, it is good for other domains. You can reproduce the evaluation result by running code python evaluationmodel.py (data downloaded from Kaggle). Contact Email: nguyennhotrung3004@gmail.com Developer Member: Nguyễn Nho Trung, Nguyễn Nhật Quang, Nguyễn Văn Huy. Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerAITeamVN
TypeEmbedding models
Parameters (lead)568M
Context8,194 tokens
Variants1
Runs withsentence-transformers
Based onBAAI/bge-m3
Released2025-04-30
Popularity31k downloads / month
Likes12
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Vietnamese_Embedding_v2568MBF16~1.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

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

Details

Languages, data & research

Languages

vi

Tags

sentence-transformers onnx safetensors xlm-roberta Embedding sentence-similarity vi text-embeddings-inference endpoints_compatible

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Vietnamese_Embedding on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

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