diff --git a/src/utils/common.py b/src/utils/common.py index 1086be35..917bd867 100644 --- a/src/utils/common.py +++ b/src/utils/common.py @@ -213,7 +213,7 @@ def load_pretrained( model = AutoModelForCausalLM.from_pretrained( model_to_load, config=config, - torch_dtype=model_args.compute_dtype, + torch_dtype=torch.bfloat16 if model_args.compute_dtype == torch.bfloat16 else torch.float16, low_cpu_mem_usage=True, **config_kwargs )