From 8efdc01ffb9346819929dd4719602be9c94bfb17 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Thu, 25 May 2023 15:05:53 -0300 Subject: [PATCH] Better default for compute_dtype --- modules/shared.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/shared.py b/modules/shared.py index c338d64f..99391f65 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -123,7 +123,7 @@ parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_ # Accelerate 4-bit parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision (using bitsandbytes).') -parser.add_argument('--compute_dtype', type=str, default="bfloat16", help="compute dtype for 4-bit. Valid options: bfloat16, float16, float32.") +parser.add_argument('--compute_dtype', type=str, default="float16", help="compute dtype for 4-bit. Valid options: bfloat16, float16, float32.") parser.add_argument('--quant_type', type=str, default="nf4", help='quant_type for 4-bit. Valid options: nf4, fp4.') parser.add_argument('--use_double_quant', action='store_true', help='use_double_quant for 4-bit.')