# Parser copied from https://github.com/vladmandic/automatic
parser=argparse.ArgumentParser(description="Text generation web UI",conflict_handler='resolve',add_help=True,formatter_class=lambdaprog:argparse.HelpFormatter(prog,max_help_position=55,indent_increment=2,width=200))
group.add_argument('--multi-user',action='store_true',help='Multi-user mode. Chat histories are not saved or automatically loaded. Warning: this is likely not safe for sharing publicly.')
group.add_argument('--character',type=str,help='The name of the character to load in chat mode by default.')
group.add_argument('--model',type=str,help='Name of the model to load by default.')
group.add_argument('--lora',type=str,nargs='+',help='The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces.')
group.add_argument('--model-dir',type=str,default='models/',help='Path to directory with all the models.')
group.add_argument('--lora-dir',type=str,default='loras/',help='Path to directory with all the loras.')
group.add_argument('--model-menu',action='store_true',help='Show a model menu in the terminal when the web UI is first launched.')
group.add_argument('--settings',type=str,help='Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml, this file will be loaded by default without the need to use the --settings flag.')
group.add_argument('--extensions',type=str,nargs='+',help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.')
group.add_argument('--verbose',action='store_true',help='Print the prompts to the terminal.')
group.add_argument('--chat-buttons',action='store_true',help='Show buttons on the chat tab instead of a hover menu.')
group.add_argument('--idle-timeout',type=int,default=0,help='Unload model after this many minutes of inactivity. It will be automatically reloaded when you try to use it again.')
group.add_argument('--loader',type=str,help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ, AutoAWQ.')
group.add_argument('--cpu',action='store_true',help='Use the CPU to generate text. Warning: Training on CPU is extremely slow.')
group.add_argument('--auto-devices',action='store_true',help='Automatically split the model across the available GPU(s) and CPU.')
group.add_argument('--gpu-memory',type=str,nargs='+',help='Maximum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs. You can also set values in MiB like --gpu-memory 3500MiB.')
group.add_argument('--cpu-memory',type=str,help='Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.')
group.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.')
group.add_argument('--disk-cache-dir',type=str,default='cache',help='Directory to save the disk cache to. Defaults to "cache".')
group.add_argument('--load-in-8bit',action='store_true',help='Load the model with 8-bit precision (using bitsandbytes).')
group.add_argument('--bf16',action='store_true',help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
group.add_argument('--no-cache',action='store_true',help='Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.')
group.add_argument('--trust-remote-code',action='store_true',help='Set trust_remote_code=True while loading the model. Necessary for some models.')
group.add_argument('--force-safetensors',action='store_true',help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.')
group.add_argument('--no_use_fast',action='store_true',help='Set use_fast=False while loading the tokenizer (it\'s True by default). Use this if you have any problems related to use_fast.')
group.add_argument('--use_flash_attention_2',action='store_true',help='Set use_flash_attention_2=True while loading the model.')
group.add_argument('--tensorcores',action='store_true',help='Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only.')
group.add_argument('--tensor_split',type=str,default=None,help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.')
group.add_argument('--numa',action='store_true',help='Activate NUMA task allocation for llama.cpp.')
group.add_argument('--logits_all',action='store_true',help='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')
group.add_argument('--no_offload_kqv',action='store_true',help='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')
group.add_argument('--cache-capacity',type=str,help='Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
group.add_argument('--streaming-llm',action='store_true',help='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
group.add_argument('--attention-sink-size',type=int,default=5,help='StreamingLLM: number of sink tokens. Only used if the trimmed prompt does not share a prefix with the old prompt.')
group.add_argument('--autosplit',action='store_true',help='Autosplit the model tensors across the available GPUs. This causes --gpu-split to be ignored.')
group.add_argument('--cfg-cache',action='store_true',help='ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
group.add_argument('--no_inject_fused_mlp',action='store_true',help='Triton mode only: disable the use of fused MLP, which will use less VRAM at the cost of slower inference.')
group.add_argument('--no_use_cuda_fp16',action='store_true',help='This can make models faster on some systems.')
group.add_argument('--desc_act',action='store_true',help='For models that do not have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
group.add_argument('--disable_exllama',action='store_true',help='Disable ExLlama kernel, which can improve inference speed on some systems.')
group.add_argument('--no_inject_fused_attention',action='store_true',help='Disable the use of fused attention, which will use less VRAM at the cost of slower inference.')
group.add_argument('--hqq-backend',type=str,default='PYTORCH_COMPILE',help='Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.')
group.add_argument('--cpp-runner',action='store_true',help='Use the ModelRunnerCpp runner, which is faster than the default ModelRunner but doesn\'t support streaming yet.')
group.add_argument('--alpha_value',type=float,default=1,help='Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.')
group.add_argument('--rope_freq_base',type=int,default=0,help='If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63).')
group.add_argument('--compress_pos_emb',type=int,default=1,help="Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.")
group.add_argument('--listen',action='store_true',help='Make the web UI reachable from your local network.')
group.add_argument('--listen-port',type=int,help='The listening port that the server will use.')
group.add_argument('--listen-host',type=str,help='The hostname that the server will use.')
group.add_argument('--share',action='store_true',help='Create a public URL. This is useful for running the web UI on Google Colab or similar.')
group.add_argument('--auto-launch',action='store_true',default=False,help='Open the web UI in the default browser upon launch.')
group.add_argument('--gradio-auth',type=str,help='Set Gradio authentication password in the format "username:password". Multiple credentials can also be supplied with "u1:p1,u2:p2,u3:p3".',default=None)
group.add_argument('--gradio-auth-path',type=str,help='Set the Gradio authentication file path. The file should contain one or more user:password pairs in the same format as above.',default=None)
group.add_argument('--ssl-keyfile',type=str,help='The path to the SSL certificate key file.',default=None)
group.add_argument('--ssl-certfile',type=str,help='The path to the SSL certificate cert file.',default=None)
group.add_argument('--admin-key',type=str,default='',help='API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key.')
group.add_argument('--nowebui',action='store_true',help='Do not launch the Gradio UI. Useful for launching the API in standalone mode.')
logger.warning("\nYou are potentially exposing the web UI to the entire internet without any access password.\nYou can create one with the \"--gradio-auth\" flag like this:\n\n--gradio-auth username:password\n\nMake sure to replace username:password with your own.")
ifargs.multi_user:
logger.warning('\nThe multi-user mode is highly experimental and should not be shared publicly.')
