Here is a prompt to granite itself plus the answer.
how many parameter do you have
Granite
Granite
As a large language model, my architecture is based on the Transformer architecture, which includes numerous learned parameters. However, I don't have direct access to specifics regarding the exact number of parameters in my model. My design and parameter values were decided upon by IBM during the development phase. It's typical for models of this scale to contain billions of parameters, which are adjusted during training on a vast corpus of text to understand and generate human-like text.
It's important to note that while the number of parameters is often discussed in AI (artificial intelligence) contexts, it's the values of these parameters, their training methods, and the architecture design that truly determine a model's capacity and performance. Simply knowing the count does not provide a complete picture of the model's capabilities or behavior.
Now a similar prompt to Copilot plus its answer
how many parameters does granite ai model have
IBM's Granite AI models come in different sizes, with parameter counts ranging from 2 billion (2B) to 8 billion (8B). These models are designed for enterprise AI applications, offering multilingual text and image processing capabilities. Some specialized versions, like Granite Code Models, have even larger variants, including 3B, 8B, 20B, and 34B parameters.
Granite models focus on efficiency, reasoning, and trustworthy AI, making them competitive with other large language models. Would you like to explore how they compare to other AI models in terms of performance and use cases?
Dealing with granite is exactly the same as dealing with IBM: you cannot possibly get a straight answer; it's all baffle-gab with no actual answers.
I bring this up because THIS is the future of the company. This is what Arvind et. al. are hanging their hats on. And it's pretty much useless. It cannot or will not answer an easy question. Even about itself. Clearly, the training is a million miles behind the big players. Just as IBM Cloud was (and is) a million miles behind the big players.