Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models
arXiv:2610.22428v1 Announce Type: new Abstract: In a small language model the vocabulary is the single largest part. In Gemma 3 270M the embedding table holds 168M of 268M parameters, and because quantisation methods leave the embedding in 16-bit, it is also most of the file once the rest of the mo…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-19 04:00 · arXiv cs.CL
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models