Text Summarization using LLAMA3.1-405b

Dataset

The benchmark implementation run command will automatically download the validation and calibration datasets and do the necessary preprocessing. In case you want to download only the datasets, you can use the below commands.

ValidationCalibration

Get Validation Dataset

mlcr get,dataset,mlperf,inference,llama3,_validation --outdirname=<path to download> -j

Get Calibration Dataset

mlcr get,dataset,mlperf,inference,llama3,_calibration --outdirname=<path to download> -j

• --outdirname=<PATH_TO_DOWNLOAD_LLAMA3_405B_DATASET> could be provided to download the dataset to a specific location.

Model

The benchmark implementation run command will automatically download the required model and do the necessary conversions. In case you want to only download the official model, you can use the below commands.

Pytorch

From MLCOMMONS Google DriveFrom Hugging Face repo

Note: One has to accept the MLCommons Llama 3.1 License Confidentiality Notice to access the model files in MLCOMMONS Google Drive.

Get the Official MLPerf LLAMA3.1-405B model from MLCOMMONS Google Drive

mlcr get,ml-model,llama3 -j

Note: Access to the HuggingFace model could be requested here.

Get model from HuggingFace repo

mlcr get,ml-model,llama3,_hf --hf_token=<huggingface access token> -j

• --outdirname=<PATH_TO_DOWNLOAD_LLAMA3_405B_MODEL> could be provided to download the model to a specific location.