From 1b99ed61bc834a76b1d436fe6e7ad411a46c8385 Mon Sep 17 00:00:00 2001 From: Ayanami Rei Date: Mon, 13 Mar 2023 20:01:34 +0300 Subject: [PATCH] add argument --gptq-model-type and remove duplicate arguments --- modules/shared.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/shared.py b/modules/shared.py index 5f6c01f3..c74117ab 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -68,8 +68,8 @@ parser.add_argument('--chat', action='store_true', help='Launch the web UI in ch parser.add_argument('--cai-chat', action='store_true', help='Launch the web UI in chat mode with a style similar to Character.AI\'s. If the file img_bot.png or img_bot.jpg exists in the same folder as server.py, this image will be used as the bot\'s profile picture. Similarly, img_me.png or img_me.jpg will be used as your profile picture.') parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text.') parser.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision.') -parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision. Currently only works with LLaMA.') -parser.add_argument('--gptq-bits', type=int, default=0, help='Load a pre-quantized model with specified precision. 2, 3, 4 and 8bit are supported. Currently only works with LLaMA.') +parser.add_argument('--gptq-bits', type=int, default=0, help='Load a pre-quantized model with specified precision. 2, 3, 4 and 8bit are supported. Currently only works with LLaMA and OPT.') +parser.add_argument('--gptq-model-type', type=str, default='llama', help='Model type of pre-quantized model. Currently only LLaMa and OPT are supported.') parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.') parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.') parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.')