14 points | by devstein 8 hours ago ago
6 comments
Feels like embeddings are underrated compared to LLM's hype, but they doing great.
I’m partial to jina.ai — they have open models for code and prose, all easily runnable locally.
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.
who knows a tool for rug check in crypto
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
embeddings are easy to fine tune. Try modern bert.
Feels like embeddings are underrated compared to LLM's hype, but they doing great.
I’m partial to jina.ai — they have open models for code and prose, all easily runnable locally.
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.
who knows a tool for rug check in crypto
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
embeddings are easy to fine tune. Try modern bert.