card: model-index benchmark metadata, retrieval tags, arxiv link, attribution + citation

README.md

@@ -19,10 +19,34 @@ tags:
   - ministral3
   - quantized
   - 4-bit
+  - information-retrieval
+  - dense-retrieval
+  - vector-search
+  - matryoshka
+  - arxiv:2502.13595
 language:
   - en
   - multilingual
 library_name: mlx
+model-index:
+  - name: Nemotron-3-Embed-8B-Community-MLX-4bit
+    results:
+      - task:
+          type: Retrieval
+        dataset:
+          name: MTEB NFCorpus
+          type: mteb/nfcorpus
+        metrics:
+          - type: ndcg_at_10
+            value: 0.4199
+      - task:
+          type: Retrieval
+        dataset:
+          name: MTEB SciFact
+          type: mteb/scifact
+        metrics:
+          - type: ndcg_at_10
+            value: 0.8338
 ---
 
 # Nemotron-3-Embed-8B — Community MLX 4-bit
@@ -105,6 +129,19 @@ Throughput saturates near 1,300–1,400 tokens/s at document lengths (memory-ban
 - `mlx-embeddings`/`mlx-lm` do not load this architecture correctly (causal attention). Use the bundled module.
 - Quantization was validated on macOS 27 / mlx 0.29; older mlx releases may not support the quantized layout.
 
+## Attribution & citation
+
+Quantization, validation harness, and card by [Matt Busi](https://huggingface.co/mattbusi) at [ShadowRock](https://www.linkedin.com/company/shadowrock). If you use this build, cite the NVIDIA base model — the embedding quality is theirs:
+
+```bibtex
+@misc{nvidia2026nemotron3embed,
+  title  = {Nemotron-3-Embed-8B},
+  author = {NVIDIA},
+  year   = {2026},
+  url    = {https://huggingface.co/nvidia/Nemotron-3-Embed-8B-BF16}
+}
+```
+
 ## License
 
 OpenMDW-1.1, inherited from the base model (see `LICENSE`). `NOTICE` carries the upstream Apache-2.0 attribution for the Ministral component plus our modification statement. Community build by [ShadowRock](https://www.linkedin.com/company/shadowrock); no NVIDIA affiliation or endorsement.