cerebras.modelzoo.common.run_gpt_inference

GPT Inference script built using the cstorch API

Functions

format_rate
get_all_checkpoints	Return the path to all available checkpoints
get_cluster_config
get_latest_checkpoint	Get the path to the checkpoint with the highest global step
get_model_checkpoint	Get the path to the model checkpoint, if any.
get_parser
inference_input_dataloader
load_from_checkpoint_file	Loads state dict from checkpoint path and checks for version compatibilty.
main
set_attention_params	Set attention-related parameters.
set_defaults	Update any missing parameters in the params dictionary with default values
setup_artifact_dir	Create a unique subdirectory for this run by generating a time stamp so that parallel runs using the same model_dir don't overwrite common files.
setup_logging	Configure default logging format.
setup_logging_excepthook	Setup a logging hook that runs whenever an exception is raised that catches and logs the exception to ensure that the full traceback is printed in the log file.

previous

cerebras.modelzoo.common.run_eleuther_eval_harness.run_eval_harness

next

cerebras.modelzoo.common.run_gpt_inference.format_rate