Minor changes

modules/models.py

@@ -47,17 +47,13 @@ def load_model(model_name):
         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:
-            model = AutoModelForCausalLM.from_pretrained(
-                Path(f"models/{shared.model_name}"),
-                low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16
-            )
+            model = AutoModelForCausalLM.from_pretrained(Path(f"models/{shared.model_name}"), low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if shared.args.bf16 else torch.float16)
             if torch.has_mps:
                 device = torch.device('mps')
                 model = model.to(device)
             else:
                 model = model.cuda()
 
-
     # FlexGen
     elif shared.args.flexgen:
         # Initialize environment
@@ -106,7 +102,7 @@ def load_model(model_name):
     # Custom
     else:
         params = {"low_cpu_mem_usage": True}
-        if not shared.args.cpu and not torch.cuda.is_available() and not torch.has_mps:
+        if not any((shared.args.cpu, torch.cuda.is_available(), torch.has_mps)):
             print("Warning: torch.cuda.is_available() returned False.\nThis means that no GPU has been detected.\nFalling back to CPU mode.\n")
             shared.args.cpu = True
 

modules/text_generation.py

@@ -39,7 +39,6 @@ def encode(prompt, tokens_to_generate=0, add_special_tokens=True):
         else:
             return input_ids.cuda()
 
-
 def decode(output_ids):
     # Open Assistant relies on special tokens like <|endoftext|>
     if re.match('(oasst|galactica)-*', shared.model_name.lower()):