Change wording to be consistent with other args

README.md

@@ -139,7 +139,7 @@ Optionally, you can use the following command-line flags:
 | `--cpu`       | Use the CPU to generate text.|
 | `--load-in-8bit`  | Load the model with 8-bit precision.|
 | `--load-in-4bit`  | Load the model with 4-bit precision. Currently only works with LLaMA.|
-| `--llama-bits`  |  Load pre-quantized models with specified precision. 2, 3, 4 and 8bit are supported. Currently only works with LLaMA. |
+| `--llama-bits`  |  Load a pre-quantized model with specified precision. 2, 3, 4 and 8bit are supported. Currently only works with LLaMA. |
 | `--bf16`  | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. |
 | `--auto-devices` | Automatically split the model across the available GPU(s) and CPU.|
 | `--disk` | If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk. |

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 pre-quantized models with specified precision. 2, 3, 4 and 8bit are supported. 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('--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.')