| --- |
| title: README |
| emoji: 🏆 |
| colorFrom: indigo |
| colorTo: blue |
| sdk: static |
| pinned: false |
| license: mit |
| --- |
| <!-- |
| QuerynAi — Hugging Face organization card. |
| Local draft (git-ignored). Paste into the org card at |
| https://huggingface.co/organizations/QuerynAi/settings → or the QuerynAi/README repo. |
| Fill the <…> placeholders before publishing. |
| --> |
|
|
| # Queryn — Embedding Translation |
|
|
| **Move a corpus between embedding models without re-embedding it.** Given a text |
| chunk's embedding in Model A's space, a Queryn adapter returns the equivalent |
| vector in Model B's space — so a vector index built with one model can be served |
| against another after a lightweight transform instead of a full, expensive |
| backfill. |
|
|
| ## What's in this org |
|
|
| The **[Queryn Embedding Adapters](https://huggingface.co/QuerynAi)** collection — |
| one small ONNX model per directed model pair (`queryn-adapter-<source>_to_<target>`). |
| Each repo contains: |
|
|
| - `model.onnx` — the adapter, opset 17, dynamic batch axis. Runs anywhere |
| `onnxruntime` runs; no PyTorch needed. |
| - `model.safetensors` — the same weights, for retraining / inspection. |
| - `config.json` — dimensions, the I/O contract, and provenance. |
| - a model card with per-pair metrics and training plots. |
|
|
| Every adapter L2-normalizes its input and output internally, so you feed raw |
| embeddings straight in and get unit vectors back. |
|
|
| ## Using an adapter |
|
|
| ```python |
| import numpy as np, onnxruntime as ort |
| from huggingface_hub import hf_hub_download |
| |
| repo = "QuerynAi/queryn-adapter-ada-002_to_bge-m3" |
| sess = ort.InferenceSession(hf_hub_download(repo, "model.onnx"), |
| providers=["CPUExecutionProvider"]) |
| |
| src = np.random.rand(8, 1536).astype(np.float32) # your ada-002 embeddings |
| tgt = sess.run(["target_embedding"], {"source_embedding": src})[0] |
| # tgt: (8, 1024) unit vectors in bge-m3 space |
| ``` |
|
|
| ## How the adapters are built |
|
|
| - One **linear** projection and one **1-hidden-layer GELU MLP** (with a |
| compressed latent below both dimensions) are trained per pair; whichever scores |
| higher on held-out cosine similarity is published, ties to linear. Each pair's |
| card reports both, so the linear-vs-nonlinear trade-off is visible. |
| - Trained on a unified **~349,674-row, five-domain corpus** (arXiv abstracts, |
| Australian case law, SQuAD passages, PubMed RCT abstracts, financial/markets |
| news), optimizing `1 − mean cosine similarity` with Adam and LR scheduling. |
| - Some embedding spaces are near-isomorphic and align well with a single matrix; |
| others need the nonlinear map and still lose accuracy. Check the card metrics |
| for your pair before relying on it — translation is an approximation, not a |
| substitute for re-embedding when fidelity is critical. |
|
|
| ## Model coverage |
|
|
| | Model | Dim | Role in v1 | |
| |---|---|---| |
| | `ada-002` | 1536 | source only (deprecated as a target) | |
| | `te3-small` | 1536 | source + target | |
| | `qwen3-emb-8b` | 4096 | source + target | |
| | `bge-m3` | 1024 | source + target | |
| | `me5-large` | 1024 | source + target | |
| | `pplx-embed-1` | 1024 | source + target | |
| | `nemotron-1b-free` | 2048 | source + target | |
| | `fastembed-bge-small` | 384 | source + target | |
|
|
| 49 directed pairs in the current (v1) generation. |
|
|
| ## Links |
|
|
| - **Code & pipeline:** <GitHub repo URL> |
| - **Training corpus + paired embeddings:** <Kaggle dataset URL> |
| - **Papers behind the approach:** Vec2Vec ([arXiv:2306.12689](https://arxiv.org/abs/2306.12689)), |
| mini-vec2vec ([arXiv:2510.02348](https://arxiv.org/abs/2510.02348)) |
|
|
| ## License |
|
|
| Adapter models: **MIT**. The Queryn codebase: **Apache-2.0**. Training data keeps |
| each source corpus's own license — see the dataset's `LICENSE` manifest. |
|
|
| ## Status |
|
|
| An independent research project on practical embedding-space alignment. Issues and |
| findings welcome via the repo; the adapters are provided as-is. |
