Update 'tortoise/utils/device.py'

Noticed that the autoregressive batch size was being set off of VRAM size. Adjusted to scale for the VRAM capacity of 90 series GPUs. In this case, 16 -> 32 batches. 

Using the standard pre-set with ChungusVGAN, I went from 16 steps to 8.
Over an average of 3 runs, I achieved an average of 294 seconds with 16 batches, to 234 seconds with 32. Can't complain at a 1.2x speed increase with functionally 2 lines of code. Can't complain. 

I restarted tortoise each run, and executing ```torch.cuda.empty_cache()``` just before loading the autoregressive model to clean the memory cache each time.

tortoise/utils/device.py

@@ -50,21 +50,32 @@ def get_device_batch_size():
     name = get_device_name()
     
     if name == "dml":
-        # there's nothing publically accessible in the DML API that exposes this
+        # there's nothing publicly accessible in the DML API that exposes this
         # there's a method to get currently used RAM statistics... as tiles
         available = 1
     elif name == "cuda":
-        _, available = torch.cuda.mem_get_info()
+        _,available = torch.cuda.mem_get_info()
     elif name == "cpu":
         available = psutil.virtual_memory()[4]
 
     availableGb = available / (1024 ** 3)
-    if availableGb > 14:
+    
+    print(f"Total device memory available: {availableGb}")
+    if availableGb > 18:
+        print(f"Setting AutoRegressive Batch Size to: 32")
+        print(f"Damn. Nice GPU Dude.")
+        return 32
+    elif availableGb > 14:
+        print(f"Setting AutoRegressive Batch Size to: 16")
         return 16
     elif availableGb > 10:
+        print(f"Setting AutoRegressive Batch Size to: 8")
         return 8
     elif availableGb > 7:
+        print(f"Setting AutoRegressive Batch Size to: 4")
         return 4
+    print(f"Setting AutoRegressive Batch Size to: 1")
+    print(f"Don't cry about it if it doesn't work.")
     return 1
 
 def get_device_count(name=get_device_name()):