Fix compression ratio (10.7x -> 32x), add GitHub link

README.md

@@ -27,12 +27,13 @@ model-index:
 **bge-large-en-v1.5 fine-tuned with RF-Snap to align embeddings to the E8 lattice.**
 
 Part of the [LatticeMemory](https://huggingface.co/spaces/dfrokido/LatticeMemory) project.
+[**GitHub →**](https://github.com/sangmorg1-debug/latticememory)
 
 ## What Makes This Different
 
 Standard embedding models output float32 vectors. This model is trained so its outputs
 naturally snap to the nearest point in the E8 lattice — the densest sphere packing in
-8 dimensions. The result: a **10.7x smaller** index with **better STS quality** than
+8 dimensions. The result: a **32x smaller** index with **better STS quality** than
 the float32 baseline.
 
 ## Benchmarks
@@ -41,10 +42,15 @@ the float32 baseline.
 |---|---|---|
 | STSBenchmark (Spearman) | 0.8637 | **0.8714** (+0.0077) |
 | STS13 | — | **0.8826** |
-| Index compression | 1x | **10.7x** |
-| Retrieval p50 @ 100K docs | 20.8 ms (scan) | **1.2 ms (O(1) hit)** |
+| Index compression | 1x | **32x** |
+| Retrieval @ 100K docs | 20.8 ms (scan) | **O(1) on E8 key hit** |
 | Recall@10 (MS-MARCO 1K) | 100% | **100%** |
 
+> **Compression basis:** 1 address byte per 8-dim block × 128 blocks = 128 bytes for a
+> 1024-dim embedding, vs 4,096 bytes for float32 = 32x. This applies to E8 key storage;
+> see [LatticeMemory](https://github.com/sangmorg1-debug/latticememory) for hybrid mode,
+> which also stores a dense fallback index for asymmetric retrieval.
+
 ## Usage
 
 ```python
@@ -54,7 +60,7 @@ import torch, math, torch.nn.functional as F
 model = SentenceTransformer("dfrokido/bge-large-e8-snap")
 embeddings = model.encode(["What is the capital of France?"], convert_to_tensor=True)
 embeddings = F.normalize(embeddings.float(), p=2, dim=1)
-# Embeddings are now ready for LatticeMemory indexing — 10.7x smaller index
+# Embeddings are now ready for LatticeMemory indexing — 32x smaller index
 ```
 
 ## Training
@@ -67,8 +73,9 @@ Fine-tuned from `BAAI/bge-large-en-v1.5` using RF-Snap training:
 
 ## LatticeMemory
 
-This model powers [LatticeMemory](https://huggingface.co/spaces/dfrokido/LatticeMemory) —
-an open knowledge infrastructure layer for AI systems. 10.7x compressed indexes,
-O(1) retrieval for domain knowledge bases, deterministic addressing.
+This model powers [LatticeMemory](https://huggingface.co/spaces/dfrokido/LatticeMemory)
+([GitHub](https://github.com/sangmorg1-debug/latticememory), `pip install latticememory`) —
+a semantic cache, dedup, and hybrid memory library for LLM applications. 32x compressed
+E8 keys for instant repeat-query cache hits, dense fallback for novel retrieval.
 
 Design partner inquiries: dfrokido@gmail.com