←back to thread

Ask HN: Is anyone doing anything cool with tiny language models?

684 points prettyblocks | 1 comments | 21 Jan 25 19:39 UTC | HN request time: 0.384s | source

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
codazoda ◴[22 Jan 25 01:08 UTC] No.42787404[source]▶
I had an LLM create a playlist for me.

I’m tired of the bad playlists I get from algorithms, so I made a specific playlist with an Llama2 based on several songs I like. I started with 50, removed any I didn’t like, and added more to fill in the spaces. The small models were pretty good at this. Now I have a decent fixed playlist. It does get “tired” after a few weeks and I need to add more to it. I’ve never been able to do this myself with more than a dozen songs.

replies(4): >>42788087 #>>42790316 #>>42792207 #>>42794243 #
jamesponddotco ◴[22 Jan 25 12:45 UTC] No.42792207[source]▶
Interesting! I wrote a prompt for something similar[1], but I use Claude Sonnet for it. I wonder how a small model would handle it. Time to test, I guess.

[1]: https://git.sr.ht/~jamesponddotco/llm-prompts/tree/trunk/dat...

replies(1): >>42797345 #
1. codazoda ◴[22 Jan 25 20:50 UTC] No.42797345[source]▶
This prompt is a lot more complex than what I did. I don’t recall my exact prompt but it was something like, “Generate a list of 25 songs that I may like if I like Girl is on my Mind by the Black Keys.”