From a4c99a529f74931160e7e2699396d65531decb07 Mon Sep 17 00:00:00 2001 From: Dipika Date: Thu, 20 Feb 2025 20:30:42 +0000 Subject: [PATCH] save commpressed by defualt --- examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py b/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py index 85cb38867..6184d4438 100644 --- a/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py +++ b/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py @@ -116,5 +116,5 @@ def get_recipe(fp8_enabled): print("==========================================\n") # Save compressed model and tokenizer -model.save_pretrained(save_dir, save_compressed=args.fp8) +model.save_pretrained(save_dir) tokenizer.save_pretrained(save_dir)