Update documentation

README.md

@@ -177,7 +177,7 @@ 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.|
 | `--wbits WBITS`            | GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. |
-| `--model_type MODEL_TYPE`  | GPTQ: Model type of pre-quantized model. Currently only LLaMA and OPT are supported. |
+| `--model_type MODEL_TYPE`  | GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. |
 | `--groupsize GROUPSIZE`    | GPTQ: Group size. |
 | `--pre_layer PRE_LAYER`    | GPTQ: The number of layers to preload. |
 | `--bf16`         | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. |

modules/GPTQ_loader.py

@@ -48,7 +48,6 @@ def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exc
 
     return model
 
-
 def load_quantized(model_name):
     if not shared.args.model_type:
         # Try to determine model type from model name

modules/shared.py

@@ -84,7 +84,7 @@ parser.add_argument('--gptq-bits', type=int, default=0, help='DEPRECATED: use --
 parser.add_argument('--gptq-model-type', type=str, help='DEPRECATED: use --model_type instead.')
 parser.add_argument('--gptq-pre-layer', type=int, default=0, help='DEPRECATED: use --pre_layer instead.')
 parser.add_argument('--wbits', type=int, default=0, help='GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
-parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently only LLaMA and OPT are supported.')
+parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
 parser.add_argument('--groupsize', type=int, default=-1, help='GPTQ: Group size.')
 parser.add_argument('--pre_layer', type=int, default=0, help='GPTQ: The number of layers to preload.')