README.md

This repository contains AWS Inferentia2 and neuronx compatible checkpoints for Mistral-Large-Instruct. You can find detailed information about the base model on its Model Card.

This model has been exported to the neuron format using specific input_shapes and compiler parameters detailed in the paragraphs below.

It has been compiled to run on an inf2.48xlarge instance on AWS. Note that while the inf2.48xlarge has 24 cores, this compilation uses 24.

SEQUENCE_LENGTH = 4096

BATCH_SIZE = 4

NUM_CORES = 24

PRECISION = "bf16"

license: other license_name: mrl license_link: LICENSE language: - en base_model: - mistralai/Mistral-Large-Instruct-2407 pipeline_tag: text-generation