julep
julep copied to clipboard
Upgrade embedding model from bge-m3 to gte-Qwen2-1.5B-instruct
trafficstars
See gte-Qwen2-1.5B-instruct -- it's both lighter-weight and more performant but key differences are:
- embedding dimensions: 1536 (instead of 1024)
- uses an instruction for the queries.