We obviously need to create a pelican bicycle svg finetune ;) If you want to try this out I'd be thrilled to do it with you, I genuinely am curious how well this model can perform if specialized on that task.

A couple colleagues of mine posted an example of finetuning a model to take on persona's for videogame NPCs. They have experience working with folks in the game industry and a use case like this is suitable for game devs who want to start including lightweight models that won't take up a ton of accelerator memory and can run efficiently on CPU if needed. https://ai.google.dev/gemma/docs/core/huggingface_text_full_...

As for GGUF it's available here! https://huggingface.co/collections/ggml-org/gemma-3-270m-689...

▲

jtolmar 6 days ago | parent | next [-]

Caves Of Qud uses Markov chain generated text to great effect in some places. I think something light that's still more competent than Markov chains has a lot of potential.

▲

srekhi 6 days ago | parent | prev | next [-]

video game NPCs with intelligence :O gaming is going to be crazy

▲

mrbonner 6 days ago | parent | prev | next [-]

Do you know that hardware required to fine-tune this model? I'm asking on behave of us GPU starve folks

▲

canyon289 6 days ago | parent [-]

A free colab. Here's a link, you can finetune the model in ~5 minutes in this example, and I encourage you to try your own

https://ai.google.dev/gemma/docs/core/huggingface_text_full_...

	▲	punnerud 6 days ago \| parent [-]
		Finally a Google guide using PyTorch and not Tensorflow, that alone made me wanting to try it out ;)

▲

megaman821 6 days ago | parent | prev | next [-]

What size of tasks can this handle? Can you do a fine-tune of Mac System Settings?

▲

canyon289 6 days ago | parent [-]

32k context window so whatever fits in there. What is a finetune of mac system settings?

▲

megaman821 6 days ago | parent | next [-]

The finetune would be an LLM where you say something like "my colors on the screen look to dark" and then it points you to Displays -> Brightness. It feels like a relatively constrained problem like finding the system setting that solves your problem is a good fit for a tiny LLM.

▲

canyon289 6 days ago | parent [-]

This would be a great experiment. I'm not sure how the OS integration would work, but as a first pass you could try finetuning the model to take natural language "my colors on the screen look to dark" and then have it output "Displays -> Brightness", then expand to the various other paths you would like the model to understand

	▲	gunalx 6 days ago \| parent [-]
		Maybe using a larger model to generate synthetic data of question path Combos, and also to rephrase and generate similar type questions for a more varier training set.

▲

hadlock 6 days ago | parent | prev [-]

It seems to dip into repeating itself pretty quickly on any task of actual complexity.

▲

AuryGlenz 6 days ago | parent | prev [-]

I have so many game ideas that would use a small LLM built up in my brain, so thank you for this.

Now if only I could somehow fine tune my life to give me more free time.