From 37685a5934fbaab100660788af8478c3c094ae68 Mon Sep 17 00:00:00 2001 From: coffee Date: Tue, 13 May 2025 17:35:26 +0800 Subject: [PATCH] add compute paramters code --- test/compute_dolly_paramters.py | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100755 test/compute_dolly_paramters.py diff --git a/test/compute_dolly_paramters.py b/test/compute_dolly_paramters.py new file mode 100755 index 0000000..24617e0 --- /dev/null +++ b/test/compute_dolly_paramters.py @@ -0,0 +1,19 @@ +# from transformers import PreTrainedModel +from transformers.modeling_utils import PreTrainedModel +import torch +from torch import nn +from src_llm.configuration_dolly import DollyConfig +from src_llm.modeling_dolly import DollyModel +# model = DollyModel(DollyConfig()) +# model.save_pretrained("./dolly_model") +# model.config.save_pretrained("./dolly_model") + +config = DollyConfig.from_pretrained("./dolly_model") +model = DollyModel.from_pretrained("./dolly_model", config=config) + +# input_ids = torch.tensor([[101, 1024, 102]]).long() +# outputs = model(input_ids) +# print(outputs) + +model_size = sum(t.numel() for t in model.parameters()) +print(f"Model Size: {model_size/1000**2:.1f}M parameters") \ No newline at end of file