A decision framework to pick the right LLM
In previous paragraphs, we covered some of the most promising Large Language Models available in the market today. Now the question is: which one should I use within my applications?The truth is that there is no a straightforward answer to this question. There are many factors to consider when choosing a large language model (LLM) for your application. Those factors also need to be declined in two scenarios: proprietary and open-source LLMs.Below you can find some factors and trade-offs you might want to consider while choosing your LLMs:
- Size and performance. We saw that complex models (that means, with high number of parameters) tend to have better performance, especially in terms of parametric knowledge and generalization capabilities. Nevertheless, the larger the model, the more computation and memory it requires to process the input and generate the output. Which can result in higher latency and, as we will see, in higher costs.
- Cost and...
