Search
Have an existing account?
Sign In
Tag: embeddings
Google folds images and audio into one Gemma embedding space
EmbeddingGemma 2 puts text, code, pictures, video and sound on a single 768-dimension vector so retrieval systems stop…
Cohere splits its new embedding model into pro and fast tiers
Cohere released Embed 5, an embedding family with pro and fast tiers that share one vector space so…
Linkup ships a sparse retriever that trains on one GPU
SPARSEUP packs a 149M-parameter encoder under Apache 2.0 weights and reports 56.4 average nDCG@10 on BEIR-13.
Pinecone open-sources a recipe book for vector quantization
Pinecone has published an MIT-licensed framework that rebuilds 25 common quantizers from seven shared primitives.
Perplexity reuses LLM kernels to keep embedding serving cheap
Engineers at Perplexity detail a GPU stack where batch and online embedding workloads borrow prefill and decode paths.