Free Databricks-Generative-AI-Engineer-Associate Actual Exam Questions - Question 4 Discussion
large language model (LLM). They need a foundation LLM with a large context window.
Which model fits this need?
DistilBERT and DBRX can be dropped since their context windows are pretty limited. Between B and C, MPT-30B is designed with extended context lengths in mind, often going beyond Llama2's standard windows. Even though Llama2-70B has some extended context versions, MPT-30B’s architecture prioritizes longer contexts out of the box, making B the more straightforward pick for a large context window need.
Makes sense to rule out DistilBERT and DBRX since they’re not known for large context windows. I agree with B since MPT-30B is built specifically to handle longer contexts than typical Llama models. B
Maybe B since MPT-30B is designed to handle extended context lengths better.
DistilBERT is mostly for smaller, efficient tasks, so probably out. Between MPT-30B and Llama2-70B, MPT might actually have a comparable or even bigger context window in some versions. Could MPT be a better fit here?
B/C? MPT-30B also supports large context windows, not just Llama2.
I'm leaning towards C. Llama2-70B because it’s known for handling larger context windows compared to DistilBERT or DBRX. MPT-30B is good but usually not as large as Llama2’s context size. Anyone else think differently?