Thread

1. vektormemory · 1790654463 · focus · HN ↗

   Can someone remove the extra LLM and just have an embedder do the classifier work?

   It's turning into pimp my llm...

   1. nojs · 1790654611 · focus · HN ↗

      Wait until you hear about support vector machines!

      1. abhgh · 1790655624 · focus · HN ↗

         Its funny - I was going to leave a similar comment - and I have, earlier, on a different thread. If people need fast classification, on a fairly scoped problem, it is very fruitful to start with an off-the-shelf embedding model like ModernBERT (which Laya uses) and stick a classifier in front - like a Support Vector Machine (SVM). For starters just tune the SVM, you don't even have to fine-tune the embedder - often it works very well, esp. given the compute needed. Plus you can get reliable confidence scores and generate explanations if you want them (using something like SHAP).
      2. baobabKoodaa · 1790671414 · focus · HN ↗

         If you have an easy problem that can be solved by a classifier from pre LLM era, then sure, go ahead. But we have LLMs now and we can use those to expensively and slowly classify harder problems using general purpose models, without needing to spend a huge amount of time fine tuning a model for the specific task. Jev offers to do the same fast and cheap.

         For clarity: no, a 0.8B model is not gonna do that.

   2. dingody · 1790667431 · focus · HN ↗

      I simply use an embedding model followed by a simple MLP, and that’s enough to solve many text classification problems.

      1. 2gay · 1790670661 · focus · HN ↗

         My little pony ?

         1. fantispug · 1790675389 · focus · HN ↗

            Multi layer perceptron. A tiny neural net.

            Boosted trees over embeddings work surprisingly well too.

   3. last_health · 1790673427 · focus · HN ↗

      [dead]

Unofficial Hacker News client; not affiliated with Y Combinator.