NVIDIA
NVIDIA
Phi-2 (TensorRT LLM)
Model
NVIDIA
NVIDIA
Phi-2 (TensorRT LLM)

Phi-2 is a 2.7 billion parameter language model developed by Microsoft Research. The phi-2 model is best suited for prompts using the Question-Answer (QA) format, the chat format, and the code format.

TRT Cloud Prebuilt Engines
TensorRT Cloud Prebuilt Engines are a set of engines for community models.