From f06a1387f0e5250ca8994320f1aaace4d07c6c34 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 6 Jun 2023 07:58:07 -0300
Subject: [PATCH] Reorganize Models tab

---
 server.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/server.py b/server.py
index e9245e81..5e770d1b 100644
--- a/server.py
+++ b/server.py
@@ -377,13 +377,12 @@ def create_model_menus():
             with gr.Box():
                 with gr.Row():
                     with gr.Column():
-                        gr.Markdown('AutoGPTQ')
+                        gr.Markdown('GPTQ')
                         shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
                         shared.gradio['desc_act'] = gr.Checkbox(label="desc_act", value=shared.args.desc_act, info='\'desc_act\', \'wbits\', and \'groupsize\' are used for old models without a quantize_config.json.')
+                        shared.gradio['gptq_for_llama'] = gr.Checkbox(label="gptq-for-llama", value=shared.args.gptq_for_llama, info='Use GPTQ-for-LLaMa loader instead of AutoGPTQ. pre_layer should be used for CPU offloading instead of gpu-memory.')
 
                     with gr.Column():
-                        gr.Markdown('GPTQ-for-LLaMa')
-                        shared.gradio['gptq_for_llama'] = gr.Checkbox(label="gptq-for-llama", value=shared.args.gptq_for_llama, info='Use GPTQ-for-LLaMa to load the GPTQ model instead of AutoGPTQ. pre_layer should be used for CPU offloading instead of gpu-memory.')
                         with gr.Row():
                             shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None")
                             shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None")