Add model card

README.md

@@ -22,7 +22,7 @@ Native **4096-bit binary** embedding model from the **Binary Native Embeddings**
 |---|---|---|---|
 | 0.7275 | 0.2958 | 500 KB | 6.0x faster at 1M vecs (FAISS AVX2+POPCNT, Intel Core Ultra 7) |
 
-Part of [binary-native-embeddings](https://github.com/korben99/binary-native-embeddings-for-CPU-Retrieval).
+Part of [binary-native-embeddings-for-CPU-Retrieval](https://github.com/korben99/binary-native-embeddings-for-CPU-Retrieval) · [Discussion](https://discuss.huggingface.co/t/native-binary-embeddings-experiment-curious-about-your-thoughts/177107)
 
 ## Why binary?
 
@@ -33,6 +33,8 @@ At 1M vectors with FAISS `IndexBinaryFlat` (AVX2 + POPCNT, Intel Core Ultra 7):
 
 POPCNT processes 64 bits/cycle; 2048-bit Hamming distance = 32 POPCNT instructions vs 384 multiply-accumulates, plus 6× better cache utilization (256 bytes/vector vs 1 536 bytes).
 
+> **Note:** float uses `IndexFlatIP` (cosine similarity) and binary uses `IndexBinaryFlat` (Hamming distance) — different metrics, but timings are comparable for measuring ranking latency at scale.
+
 ## Usage
 
 ```python