Back to News
Advertisement

Ask HN: Best Embedding Models?

ddevstein about 5 hours ago 3 comments

DE version is available. Content is displayed in original English for accuracy.

Hey HN, which embedding models are people using? There has been so much development around foundational LLMs, but haven't seen much news about embedding models.
Advertisement

⚡ Community Insights

Discussion Sentiment

50% Positive

Analyzed from 51 words in the discussion.

Trending Topics

#qwen#liked#embeddinggemma#local#search#enough#basically#fit#whole#page

Discussion (3 Comments)Read Original on HackerNews

rapatel0•about 5 hours ago
I've liked qwen and embeddinggemma for local search. Qwen because 32K is enough to basically fit a whole page into the context window and embeddiggemma because it's crazy efficient.
PhilippGille•about 2 hours ago
Benchmarks only paint part of the picture, but it's still a decent place to start looking into recent models:

https://huggingface.co/spaces/mteb/leaderboard

jayshah5696•about 3 hours ago
embeddings are easy to fine tune. Try modern bert.