Which is a valid criterion for choosing a foundation model?
Why C is the answer
Cost, modality, latency and model size
Cost, modality, latency and model size all affect whether a foundation model fits your use case.
In detail
- Cost, modality, latency and size all affect fit.
- Test candidates on your own task.
Use case
An illustrative scenario, not a real incident.
A voice app needs low latency, and a report tool needs low cost, so each chooses a different model.
See it in different ways
stateDiagram-v2 [*] --> InContext: prompt examples InContext --> Rag: needs your data Rag --> FineTuning: needs your style FineTuning --> PreTraining: rarely, a new model
mindmap
root(("Choosing a model"))
n1["Fit"]
n2["Modality"]
n3["Size"]
n4["Delivery"]
n5["Latency"]
n6["Cost"]Key point: Compare models on real criteria.
Why the other options are wrong
- A. The size of the provider's sales team
- A sales team does not affect fit.
- B. How often the provider releases a new model
- Release cadence does not show fit.
- D. The country where the provider is headquartered
- Headquarters location does not affect fit.