While any number of AI solutions are leveraging existing Large Language Models, there are still a number of startup folks creating their own models — when they can find the compute to do so. But what does it take to create those models and how does one fine tune them so that they behave as expected? Portland serial founder Devin Gaffney shared his thoughts.
To “make” a model a “specialist”, we engage in a “finetuning” procedure. Lots of companies provide this as an extension of their core models, but we can also just as easily do it with offline models. When we “fine-tune” a model, we are, in essence, teaching a machine to shift its attentional dimensions to the sub-territory of linguistic space on a “map” – we’re doing the model equivalent of zooming into a map to consider the detail we actually care about.
It’s still early days with LLMs, relatively speaking. It’s become super easy to deploy models, run them offline, and play with their output, but there’s surprisingly few rigorous, concrete results when asking a question like “How much data is enough for finetuning an LLM, though?”
For Devin’s thoughts, read “How Much Data is Enough for Finetuning an LLM?“
More Portland startup news
