README.md

metadata

tags:
  - neuron
  - optimized
  - aws-neuron
  - text-generation
base_model: microsoft/Phi-3-mini-4k-instruct

Neuron-Optimized microsoft/Phi-3-mini-4k-instruct

This repository contains AWS Neuron-optimized files for microsoft/Phi-3-mini-4k-instruct.

Model Details

• Base Model: microsoft/Phi-3-mini-4k-instruct
• Task: text-generation
• Optimization: AWS Neuron compilation
• Generated by: badaoui
• Generated using: Optimum Neuron Compiler Space

Usage

This model has been optimized for AWS Neuron devices (Inferentia/Trainium). To use it:

from optimum.neuron import NeuronModelForCausalLM

model = NeuronModelForCausalLM.from_pretrained("badaoui/microsoft-Phi-3-mini-4k-instruct-neuron")

Performance

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.

Original Model

For the original model, training details, and more information, please visit: microsoft/Phi-3-mini-4k-instruct