this post was submitted on 22 Nov 2023
1 points (100.0% liked)

Machine Learning

1 readers
1 users here now

Community Rules:

founded 1 year ago
MODERATORS
 

I'm trying to test more embedding models and I'm wondering what does this community use...

I know that it "may vary depending on use case", so in that case please share model and related use case.

Currently I'm using mostly bge-large-v1.5 or instructor-xl...

(intrested in both bi encoder and cross encoder)

Thanks im advance!!!

top 3 comments
sorted by: hot top controversial new old
[–] KingsmanVince@alien.top 1 points 11 months ago

I know that it "may vary depending on use case", so in that case please share model related use case.

related use case.

Currently I'm using mostly bge-large-v1.5 or instructor-xl...

And what's your usecase?

[–] r_s_s_i_u@alien.top 1 points 11 months ago

As you said, it depends but my to go has been Sentence transformersSBert due to its effectiveness. But if you have access to sufficient compute or it's for offline use case (i.e get embeddings once and just keep refusing them), embeddings from LLMs works well on most use cases

[–] mulleremanuelle@alien.top 1 points 11 months ago

i've been experimenting with various embedding models and was curious to know what the community prefers. i understand that it may differ based on use case, so please share the model and its related use case. currently, i'm mostly using bge-large-v1.5 and instructor-xl. i'm interested in both bi encoder and cross encoder. thanks in advance!