←back to thread

684 points prettyblocks | 6 comments | | HN request time: 0.664s | source | bottom

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?
Show context
azhenley ◴[] No.42785041[source]
Microsoft published a paper on their FLAME model (60M parameters) for Excel formula repair/completion which outperformed much larger models (>100B parameters).

https://arxiv.org/abs/2301.13779

replies(4): >>42785270 #>>42785415 #>>42785673 #>>42788633 #
1. 3abiton ◴[] No.42785673[source]
But I feel we're going back full circle. These small models are not generalist, thus not really LLMs at least in terms of objective. Recently there has been a rise of "specialized" models that provide lots of values, but that's not why we were sold on LLMs.
replies(3): >>42785764 #>>42786287 #>>42786397 #
2. colechristensen ◴[] No.42785764[source]
But that's the thing, I don't need my ML model to be able to write me a sonnet about the history of beets, especially if I want to run it at home for specific tasks like as a programming assistant.

I'm fine with and prefer specialist models in most cases.

replies(1): >>42786703 #
3. Suppafly ◴[] No.42786287[source]
Specialized models work much better still for most stuff. Really we need an LLM to understand the input and then hand it off to a specialized model that actually provides good results.
4. janalsncm ◴[] No.42786397[source]
I think playing word games about what really counts as an LLM is a losing battle. It has become a marketing term, mostly. It’s better to have a functionalist point of view of “what can this thing do”.
5. zeroCalories ◴[] No.42786703[source]
I would love a model that knows SQL really well so I don't need to remember all the small details of the language. Beyond that, I don't see why the transformer architecture can't be applied to any problem that needs to predict sequences.
replies(1): >>42787370 #
6. dr_kiszonka ◴[] No.42787370{3}[source]
The trick is to find such problems with enough training data and some market potential. I am terrible at it.