Model reference · open weights
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.
About
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
| Maker | dxtech-asia |
|---|---|
| Type | Embedding models |
| Context | 128k tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Released | 2026-08-09 |
| Popularity | 3k downloads / month |
| Likes | 27 |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| deepx-embedding-v1 | — | BF16 | — | — | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Retrieval | Zalo Legal Text Retrieval | ndcg_at_10 | 0.816 |
| Retrieval | Zalo Legal Text Retrieval | mrr_at_10 | 0.767 |
| Retrieval | Zalo Legal Text Retrieval | recall_at_10 | 0.954 |
Using it via the API
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
Trained / evaluated on
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore