text-generation-webui/modules/shared.py

import argparse

model = None
tokenizer = None
model_name = ""
soft_prompt_tensor = None
soft_prompt = False
stop_everything = False
settings = {}

parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpFormatter(prog,max_help_position=54))
parser.add_argument('--model', type=str, help='Name of the model to load by default.')
parser.add_argument('--notebook', action='store_true', help='Launch the web UI in notebook mode, where the output is written to the same text box as the input.')
parser.add_argument('--chat', action='store_true', help='Launch the web UI in chat mode.')
parser.add_argument('--cai-chat', action='store_true', help='Launch the web UI in chat mode with a style similar to Character.AI\'s. If the file img_bot.png or img_bot.jpg exists in the same folder as server.py, this image will be used as the bot\'s profile picture. Similarly, img_me.png or img_me.jpg will be used as your profile picture.')
parser.add_argument('--picture', action='store_true', help='Adds an ability to send pictures in chat UI modes. Captions are generated by BLIP.')
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('--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.')
parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".')
parser.add_argument('--gpu-memory', type=int, help='Maximum GPU memory in GiB to allocate. This is useful if you get out of memory errors while trying to generate text. Must be an integer number.')
parser.add_argument('--cpu-memory', type=int, help='Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.')
parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.')
parser.add_argument('--percent', nargs="+", type=int, default=[0, 100, 100, 0, 100, 0], help='FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0).')
parser.add_argument("--compress-weight", action="store_true", help="FlexGen: activate weight compression.")
parser.add_argument('--deepspeed', action='store_true', help='Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.')
parser.add_argument('--nvme-offload-dir', type=str, help='DeepSpeed: Directory to use for ZeRO-3 NVME offloading.')
parser.add_argument('--local_rank', type=int, default=0, help='DeepSpeed: Optional argument for distributed setups.')
parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time. This improves the text generation performance.')
parser.add_argument('--settings', type=str, help='Load the default interface settings from this json file. See settings-template.json for an example.')
parser.add_argument('--extensions', type=str, help='The list of extensions to load. If you want to load more than one extension, write the names separated by commas and between quotation marks, "like,this".')
parser.add_argument('--listen', action='store_true', help='Make the web UI reachable from your local network.')
parser.add_argument('--listen-port', type=int, help='The listening port that the server will use.')
parser.add_argument('--share', action='store_true', help='Create a public URL. This is useful for running the web UI on Google Colab or similar.')
parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.')
args = parser.parse_args()