From 265ba384b7e5e928d97d2749b25771b7d3d93fde Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 14 Mar 2023 07:56:31 -0300
Subject: [PATCH] Rename a file, add deprecation warning for --load-in-4bit

---
 modules/{quant_loader.py => GPTQ_loader.py} | 0
 modules/models.py                           | 2 +-
 modules/shared.py                           | 6 ++++++
 3 files changed, 7 insertions(+), 1 deletion(-)
 rename modules/{quant_loader.py => GPTQ_loader.py} (100%)

diff --git a/modules/quant_loader.py b/modules/GPTQ_loader.py
similarity index 100%
rename from modules/quant_loader.py
rename to modules/GPTQ_loader.py
diff --git a/modules/models.py b/modules/models.py
index 46cd77ff..f4bb11fd 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -89,7 +89,7 @@ def load_model(model_name):
 
     # Quantized model
     elif shared.args.gptq_bits > 0:
-        from modules.quant_loader import load_quantized
+        from modules.GPTQ_loader import load_quantized
 
         model = load_quantized(model_name)
 
diff --git a/modules/shared.py b/modules/shared.py
index 3abdc551..ea2eb50b 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -69,6 +69,7 @@ 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='DEPRECATED: use --gptq-bits 4 instead.')
 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, 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.')
@@ -95,3 +96,8 @@ parser.add_argument('--share', action='store_true', help='Create a public URL. T
 parser.add_argument('--auto-launch', action='store_true', default=False, help='Open the web UI in the default browser upon launch.')
 parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.')
 args = parser.parse_args()
+
+# Provisional, this will be deleted later
+if args.load_in_4bit:
+    print("Warning: --load-in-4bit is deprecated and will be removed. Use --gptq-bits 4 instead.\n")
+    args.gptq_bits = 4