diff --git a/fake_quant/utils.py b/fake_quant/utils.py index d0c0f7c..31b8276 100644 --- a/fake_quant/utils.py +++ b/fake_quant/utils.py @@ -7,7 +7,6 @@ from datetime import datetime import logging - from accelerate import dispatch_model, infer_auto_device_map from accelerate.utils import get_balanced_memory @@ -16,9 +15,13 @@ 'meta-llama/Llama-2-13b-hf', 'meta-llama/Llama-2-70b-hf', 'meta-llama/Meta-Llama-3-8B', + 'meta-llama/Meta-Llama-3-70B', + 'meta-llama/Llama-3.1-8B', + 'meta-llama/Llama-3.1-70B', + 'meta-llama/Llama-3.1-405B', 'meta-llama/Llama-3.2-1B', 'meta-llama/Llama-3.2-3B', - 'facebook/opt-125m' + 'facebook/opt-125m', ] supported_datasets = ['wikitext2', 'ptb', 'c4']