Model reference · open weights

deepx-embedding

deepx-embedding is an open-weight embedding model from dxtech-asia, 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 dxtech-asia 1 variants 3k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What deepx-embedding is

DeepX Embedding v1.0 Vietnamese Legal Document Retrieval — State-of-the-Art 🌐 Blog Post | 💻 GitHub DeepX Embedding v1.0 is a 772M parameter embedding model optimized for Vietnamese legal document retrieval. It combines Gated DeltaNet-2 linear attention (O(n)) with Hyperloop weight sharing to achieve strong retrieval quality while maintaining constant throughput regardless of sequence length. nDCG@10 = 0.8162 on Zalo Legal Text Retrieval — surpassing previous SOTA (0.7813) by +4.5%. Benchmark Results Key Features - Linear attention O(n) — Gated DeltaNet-2: processes 8K tokens with same VRAM as 512 tokens - Hyperloop architecture — 35 compute passes from only 9 unique layer parameter sets - Matryoshka embeddings — Quality at any dimension from 256d to 1536d - ColBERT dual output — Single vector (1536d) for ANN search + token vectors (128d) for MaxSim reranking - Custom vocabulary — 186,046 tokens optimized for Vietnamese + English - YaRN RoPE — 8K tokens validated, 128K supported Architecture Total: 35 compute passes. Per-loop LoRA + RoDE (Rotary Depth Embedding) differentiate each iteration. Model Size Gated DeltaNet-2 (GDN-2) Pure linear attention with O(n) complexity. Each layer maintains a running state updated via learned decay, erase, and write gates: No KV cache, no quadratic slowdown. Uses FLA (flash-linear-attention) Triton kernels for efficient chunk-parallel training. Training Training pipeline: conservative training → long-sequence expose (4K-8K) → hard negative mining → domain boost. Usage Inference Speed On RTX 5070 Ti, FP16 inference. Citation License Apache 2.0

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

Specifications

What it is

Makerdxtech-asia
TypeEmbedding models
Context128k tokens
Variants1
Runs withsentence-transformers
Released2026-08-09
Popularity3k downloads / month
Likes27
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
deepx-embedding-v1BF16Weights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
RetrievalZalo Legal Text Retrievalndcg_at_100.816
RetrievalZalo Legal Text Retrievalmrr_at_100.767
RetrievalZalo Legal Text Retrievalrecall_at_100.954

Using it via the API

Call it like any OpenAI endpoint

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

Details

Languages, data & research

Languages

vi en

Trained / evaluated on

unicamp-dl/mmarco miracl/miracl GreenNode/zalo-ai-legal-text-retrieval-vn

Tags

sentence-transformers deepx-embedding feature-extraction sentence-similarity embedding retrieval vietnamese legal linear-attention gated-deltanet matryoshka vi en dataset:unicamp-dl/mmarco

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 deepx-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