Rename --llama-bits to --gptq-bits

modules/models.py

@@ -42,7 +42,7 @@ def load_model(model_name):
     shared.is_RWKV = model_name.lower().startswith('rwkv-')
 
     # Default settings
-    if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.load_in_4bit, shared.args.llama_bits > 0, shared.args.auto_devices, shared.args.disk, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.deepspeed, shared.args.flexgen, shared.is_RWKV]):
+    if not any([shared.args.cpu, shared.args.load_in_8bit, shared.args.load_in_4bit, shared.args.gptq_bits > 0, shared.args.auto_devices, shared.args.disk, shared.args.gpu_memory is not None, shared.args.cpu_memory is not None, shared.args.deepspeed, shared.args.flexgen, shared.is_RWKV]):
         if any(size in shared.model_name.lower() for size in ('13b', '20b', '30b')):
             model = AutoModelForCausalLM.from_pretrained(Path(f"models/{shared.model_name}"), device_map='auto', load_in_8bit=True)
         else:
@@ -88,7 +88,7 @@ def load_model(model_name):
         return model, tokenizer
 
     # 4-bit LLaMA
-    elif shared.args.llama_bits > 0 or shared.args.load_in_4bit:
+    elif shared.args.gptq_bits > 0 or shared.args.load_in_4bit:
         from modules.quantized_LLaMA import load_quantized_LLaMA
 
         model = load_quantized_LLaMA(model_name)

modules/quantized_LLaMA.py

@@ -16,7 +16,7 @@ def load_quantized_LLaMA(model_name):
     if shared.args.load_in_4bit:
         bits = 4
     else:
-        bits = shared.args.llama_bits
+        bits = shared.args.gptq_bits
 
     path_to_model = Path(f'models/{model_name}')
     pt_model = ''

modules/shared.py

@@ -68,7 +68,7 @@ parser.add_argument('--cai-chat', action='store_true', help='Launch the web UI i
 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('--llama-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.')
 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.')