Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 18:45:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Update documentation

Browse source
This commit is contained in:
oobabooga 2023-03-28 17:46:00 -03:00
parent 0bec15ebcd
commit 010b259dde
3 changed files with 2 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -177,7 +177,7 @@ Optionally, you can use the following command-line flags:
| `--cpu` | Use the CPU to generate text.| | `--cpu` | Use the CPU to generate text.|
| `--load-in-8bit` | Load the model with 8-bit precision.| | `--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. | | `--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. | | `--groupsize GROUPSIZE` | GPTQ: Group size. |
| `--pre_layer PRE_LAYER` | GPTQ: The number of layers to preload. | | `--pre_layer PRE_LAYER` | GPTQ: The number of layers to preload. |
| `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. | | `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. |

1
modules/GPTQ_loader.py
View file

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

2
modules/shared.py
View file

@ -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-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('--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('--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('--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.') parser.add_argument('--pre_layer', type=int, default=0, help='GPTQ: The number of layers to preload.')