▲Scene_Cast26 hours ago
[-] Hasn't this been the case for a while? I vaguely remember using the optimal e8 packing to try to get denser product quantization for vector embeddings.
reply▲How did you apply e8 to vector embeddings?
reply▲Scene_Cast23 hours ago
[-] Chunk up your 128D embedding into 16 8D pieces, then quantize using the optimal packing points. Performs worse than k-means in my experience.
reply