|
>Where do these improvement curves go? Nowhere. Large models haven't seen that much improvement, just small unique tasks performance which is all special cased RLed to game metrics For local models, its the same story. You can download Gemma 3 QAT from last year, and it will be just as good as Gemma:31b on the average. Qwen also boasts that its better, because again, they RLed it to game some metrics. Its better in coding then Gemma, but Gemma is better in more creative thinking (again, all RL) Fundamentally, you need detail in the gradients for the models to pick up on the smaller details. If you don't have those, your output is gonna suck. No amount of clever architecture is going to fix this. The only way to improve local models by training them to fetch context, and then their job becomes much simpler because all they need to do is reinterpret the fetched content and provide an answer. But fundamentally, if you are trying to keep things in house for advertising purposes like what all companies do with search, you want them to go to your service, which means running on your servers. And its not really that much extra per invocation (i.e excluding initial hardware costs) to instead just offer a large model as a service, which will be way better than any small models. |