From d4cdd6259eafe886ccbdda44be5523faed645656 Mon Sep 17 00:00:00 2001 From: Michael Cusack Date: Fri, 4 Aug 2023 17:30:05 +0700 Subject: [PATCH] Zero'ing params docs --- save_model.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/save_model.py b/save_model.py index 4aebef0..f3b7539 100644 --- a/save_model.py +++ b/save_model.py @@ -5,6 +5,13 @@ The resulting file can be loaded in C++ code and then used for training or inference with: #include torch::jit::Module module = torch::jit::load("model.pt") + +Note that the model includes the initial parameters and with default ModelArgs the serialized model +is 59M and gzips down to 55M. If you want to serialize/distribute the model parameters separately +and the size of the model file you can zero out the parameters before saving it and it will gzip +down to 780K: + for p in model.parameters(): + p.detach().zero_() """ import glob