This repository contains AWS Neuron-optimized files for
microsoft/Phi-3-mini-4k-instruct.
This model has been optimized for AWS Neuron devices (Inferentia/Trainium). To use it:
1from optimum.neuron import NeuronModelForCausalLM
2
3model = NeuronModelForCausalLM.from_pretrained("badaoui/microsoft-Phi-3-mini-4k-instruct-neuron")
These files are pre-compiled for AWS Neuron devices and should provide improved inference performance compared to the original model when deployed on Inferentia or Trainium instances.
For the original model, training details, and more information, please visit:
microsoft/Phi-3-mini-4k-instruct