LumynaX model-infusion release by AbteeX AI Labs.
Public, non-gated package with runnable local instructions, provenance metadata, checksums, and a release manifest.
Quickstart | Model profile | Runtime files | Provenance | Validation | Limitations
      ## Executive Summary This repository is a complete LumynaX release package for `AbteeXAILab/lumynax-embed-bge-m3`. It is intended to be downloaded as a whole repo, not as a single loose weight file: the model artifact, `quickstart.py`, `requirements.txt`, `release_export_manifest.json`, `checksums.sha256`, license notice, and optional Ollama or Space files are part of the same release contract. LumynaX-infused means the upstream artifact is presented through the LumynaX release layer: local-first runtime scaffolding, LumynaX assistant identity, inference-chain metadata, public documentation, integrity files, and Aotearoa New Zealand-oriented workflow positioning. The release manifest records this as a LumynaX packaging and inference-chain layer around the listed upstream artifact; it does not claim a private LumynaX weight merge. ## AbteeX LumynaX Public Surface This card follows the AbteeX/LumynaX public-facing system used across the release family: warm paper background visuals, black editorial typography, amber proof markers, compact evidence tables, and plain-language runtime instructions. The goal is not decoration; it is operational clarity. A downloader should immediately understand what the package is, what files belong together, what runtime path is expected, what provenance is available, and what limits still apply. ## Sovereignty And Run Contract | Field | Value | | --- | --- | | Public surface | AbteeX/LumynaX light editorial system: warm paper, black ink, amber status markers, and evidence-first tables. | | Sovereign intent | Package is documented for local-first use, explicit provenance, and controlled deployment near governed data. | | Runtime residency | `python_embedding` runtime can be deployed by the user in their own approved environment. | | Model artifact | `merged_model/pytorch_model.bin` must stay with manifest, checksums, quickstart, requirements, and license files. | | Modalities | `text, embedding` | | License discipline | `mit` metadata is surfaced so downstream users can check redistribution and usage terms. | | Audit expectation | Record repo id, artifact checksum, runtime command, prompt template, operator, and deployment environment for production use. | | Router readiness | Compatible with the LumynaX MaramaRoute registry pattern for sovereign model selection and fallback planning. | ## Quickstart ```bash hf download AbteeXAILab/lumynax-embed-bge-m3 --local-dir lumynax-embed-bge-m3 cd lumynax-embed-bge-m3 pip install -r requirements.txt python quickstart.py ``` Embedding smoke command: ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("AbteeXAILab/lumynax-embed-bge-m3", trust_remote_code=True) vectors = model.encode(["LumynaX local retrieval package"]) print(vectors.shape) ``` ## Model Profile | Field | Value | | --- | --- | | Release | `LumynaX Embed BGE M3` | | Repository | `AbteeXAILab/lumynax-embed-bge-m3` | | Mode | `Retrieval and embedding package` | | Runtime | `python_embedding` | | Prompt format | `embedding` | | Modalities | `text, embedding` | | Primary artifact | `merged_model/pytorch_model.bin` | | Detected weight size | `2.12 GB` | | Package state | `upstream_weights_hydrated_embedding` | | Delivery | `standalone_hf_embedding_release` | | Upstream/base | `BAAI/bge-m3` | | Upstream kind | `official_base_weights` | | Source GGUF | `not applicable` | | Quantization | `See manifest` | | License metadata | `mit` | | Refreshed | `2026-05-11` | ## Runtime Path
