This is a collection of more than 25 types of embedding models and a really brief introduction to what you should know about embedding.If you don't keep a few things in mind, you won't be satisfied with the results. at end of the file list press to see all files All models tested with ALLM(AnythingLLM) with LM Studio as server, all models should be work with ollama the setup for local documents described below is allmost the same, GPT4All has only one model (nomic), and koboldcpp and JAN(Menlo) is not build in right now but in development I would always use f32 or f16 bit quality! (sometimes the results are more truthful if the “chat with document only” option is used) Incidentally, the Embedder model is only one part of a good RAG (Retrieval Augmented Generation), but it should be tailored to your language and, if you want it to be completely accurate, also to the application, e.g. programming or medicine. & x21e8; give me a ❤️, if you like ;) My short impression: nomic embed text v2 moe (up to 512t context length) mxbai embed large (small and fast model) mug b 1.6 qwen3 0.6b (slow but with 32k context but such large context is useless for usual queries/retrieval) jinaai v5 retrie…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy