File size: 16,196 Bytes
7ff6917 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 |
import argparse
from collections import OrderedDict
from pathlib import Path
import yaml
from modules.logging_colors import logger
generation_lock = None
model = None
tokenizer = None
is_seq2seq = False
model_name = "None"
lora_names = []
model_dirty_from_training = False
# Chat variables
stop_everything = False
processing_message = '*Is typing...*'
# UI elements (buttons, sliders, HTML, etc)
gradio = {}
# For keeping the values of UI elements on page reload
persistent_interface_state = {}
input_params = [] # Generation input parameters
reload_inputs = [] # Parameters for reloading the chat interface
# For restarting the interface
need_restart = False
# To prevent the persistent chat history from being loaded when
# a session JSON file is being loaded in chat mode
session_is_loading = False
settings = {
'dark_theme': True,
'autoload_model': False,
'max_new_tokens': 200,
'max_new_tokens_min': 1,
'max_new_tokens_max': 4096,
'auto_max_new_tokens': False,
'seed': -1,
'character': 'None',
'name1': 'You',
'name2': 'Assistant',
'context': 'This is a conversation with your Assistant. It is a computer program designed to help you with various tasks such as answering questions, providing recommendations, and helping with decision making. You can ask it anything you want and it will do its best to give you accurate and relevant information.',
'greeting': '',
'turn_template': '',
'custom_stopping_strings': '',
'stop_at_newline': False,
'add_bos_token': True,
'ban_eos_token': False,
'skip_special_tokens': True,
'truncation_length': 2048,
'truncation_length_min': 0,
'truncation_length_max': 16384,
'mode': 'chat',
'start_with': '',
'chat_style': 'TheEncrypted777',
'instruction_template': 'None',
'chat-instruct_command': 'Continue the chat dialogue below. Write a single reply for the character "<|character|>".\n\n<|prompt|>',
'chat_generation_attempts': 1,
'chat_generation_attempts_min': 1,
'chat_generation_attempts_max': 10,
'default_extensions': [],
'chat_default_extensions': ['gallery'],
'preset': 'simple-1',
'prompt': 'QA',
}
def str2bool(v):
if isinstance(v, bool):
return v
if v.lower() in ('yes', 'true', 't', 'y', '1'):
return True
elif v.lower() in ('no', 'false', 'f', 'n', '0'):
return False
else:
raise argparse.ArgumentTypeError('Boolean value expected.')
parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpFormatter(prog, max_help_position=54))
# Basic settings
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 with a style similar to the Character.AI website.')
parser.add_argument('--multi-user', action='store_true', help='Multi-user mode. Chat histories are not saved or automatically loaded. WARNING: this is highly experimental.')
parser.add_argument('--character', type=str, help='The name of the character to load in chat mode by default.')
parser.add_argument('--model', type=str, help='Name of the model to load by default.')
parser.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.')
parser.add_argument("--model-dir", type=str, default='models/', help="Path to directory with all the models")
parser.add_argument("--lora-dir", type=str, default='loras/', help="Path to directory with all the loras")
parser.add_argument('--model-menu', action='store_true', help='Show a model menu in the terminal when the web UI is first launched.')
parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time.')
parser.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.')
parser.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.')
parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.')
# Model loader
parser.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: transformers, autogptq, gptq-for-llama, exllama, exllama_hf, llamacpp, rwkv')
# Accelerate/transformers
parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text. Warning: Training on CPU is extremely slow.')
parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.')
parser.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.')
parser.add_argument('--cpu-memory', type=str, help='Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.')
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('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision (using bitsandbytes).')
parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
parser.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces the VRAM usage a bit at a performance cost.')
parser.add_argument('--xformers', action='store_true', help="Use xformer's memory efficient attention. This should increase your tokens/s.")
parser.add_argument('--sdp-attention', action='store_true', help="Use torch 2.0's sdp attention.")
parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_remote_code=True while loading a model. Necessary for ChatGLM and Falcon.")
# Accelerate 4-bit
parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision (using bitsandbytes).')
parser.add_argument('--compute_dtype', type=str, default="float16", help="compute dtype for 4-bit. Valid options: bfloat16, float16, float32.")
parser.add_argument('--quant_type', type=str, default="nf4", help='quant_type for 4-bit. Valid options: nf4, fp4.')
parser.add_argument('--use_double_quant', action='store_true', help='use_double_quant for 4-bit.')
# llama.cpp
parser.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
parser.add_argument('--n_batch', type=int, default=512, help='Maximum number of prompt tokens to batch together when calling llama_eval.')
parser.add_argument('--no-mmap', action='store_true', help='Prevent mmap from being used.')
parser.add_argument('--low-vram', action='store_true', help='Low VRAM Mode')
parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
parser.add_argument('--n_ctx', type=int, default=2048, help='Size of the prompt context.')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='Seed for llama-cpp models. Default 0 (random)')
parser.add_argument('--n_gqa', type=int, default=0, help='grouped-query attention. Must be 8 for llama-2 70b.')
parser.add_argument('--rms_norm_eps', type=float, default=0, help='5e-6 is a good value for llama-2 models.')
# GPTQ
parser.add_argument('--wbits', type=int, default=0, help='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='Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
parser.add_argument('--groupsize', type=int, default=-1, help='Group size.')
parser.add_argument('--pre_layer', type=int, nargs="+", help='The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. For multi-gpu, write the numbers separated by spaces, eg --pre_layer 30 60.')
parser.add_argument('--checkpoint', type=str, help='The path to the quantized checkpoint file. If not specified, it will be automatically detected.')
parser.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.')
parser.add_argument('--quant_attn', action='store_true', help='(triton) Enable quant attention.')
parser.add_argument('--warmup_autotune', action='store_true', help='(triton) Enable warmup autotune.')
parser.add_argument('--fused_mlp', action='store_true', help='(triton) Enable fused mlp.')
# AutoGPTQ
parser.add_argument('--gptq-for-llama', action='store_true', help='DEPRECATED')
parser.add_argument('--autogptq', action='store_true', help='DEPRECATED')
parser.add_argument('--triton', action='store_true', help='Use triton.')
parser.add_argument('--no_inject_fused_attention', action='store_true', help='Do not use fused attention (lowers VRAM requirements).')
parser.add_argument('--no_inject_fused_mlp', action='store_true', help='Triton mode only: Do not use fused MLP (lowers VRAM requirements).')
parser.add_argument('--no_use_cuda_fp16', action='store_true', help='This can make models faster on some systems.')
parser.add_argument('--desc_act', action='store_true', help='For models that don\'t have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
# ExLlama
parser.add_argument('--gpu-split', type=str, help="Comma-separated list of VRAM (in GB) to use per GPU device for model layers, e.g. 20,7,7")
parser.add_argument('--max_seq_len', type=int, default=2048, help="Maximum sequence length.")
# DeepSpeed
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.')
# RWKV
parser.add_argument('--rwkv-strategy', type=str, default=None, help='RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8".')
parser.add_argument('--rwkv-cuda-on', action='store_true', help='RWKV: Compile the CUDA kernel for better performance.')
# RoPE
parser.add_argument('--compress_pos_emb', type=int, default=1, help="Positional embeddings compression factor. Should typically be set to max_seq_len / 2048.")
parser.add_argument('--alpha_value', type=int, default=1, help="Positional embeddings alpha factor for NTK RoPE scaling. Scaling is not identical to embedding compression. Use either this or compress_pos_emb, not both.")
# Gradio
parser.add_argument('--listen', action='store_true', help='Make the web UI reachable from your local network.')
parser.add_argument('--listen-host', type=str, help='The hostname that the server will use.')
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('--auto-launch', action='store_true', default=False, help='Open the web UI in the default browser upon launch.')
parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
parser.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 this format: "u1:p1,u2:p2,u3:p3"', default=None)
parser.add_argument("--ssl-keyfile", type=str, help='The path to the SSL certificate key file.', default=None)
parser.add_argument("--ssl-certfile", type=str, help='The path to the SSL certificate cert file.', default=None)
# API
parser.add_argument('--api', action='store_true', help='Enable the API extension.')
parser.add_argument('--api-blocking-port', type=int, default=5000, help='The listening port for the blocking API.')
parser.add_argument('--api-streaming-port', type=int, default=5005, help='The listening port for the streaming API.')
parser.add_argument('--public-api', action='store_true', help='Create a public URL for the API using Cloudfare.')
# Multimodal
parser.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.')
args = parser.parse_args()
args_defaults = parser.parse_args([])
# Deprecation warnings
if args.autogptq:
logger.warning('--autogptq has been deprecated and will be removed soon. Use --loader autogptq instead.')
args.loader = 'autogptq'
if args.gptq_for_llama:
logger.warning('--gptq-for-llama has been deprecated and will be removed soon. Use --loader gptq-for-llama instead.')
args.loader = 'gptq-for-llama'
# Security warnings
if args.trust_remote_code:
logger.warning("trust_remote_code is enabled. This is dangerous.")
if args.share:
logger.warning("The gradio \"share link\" feature uses a proprietary executable to create a reverse tunnel. Use it with care.")
if args.multi_user:
logger.warning("The multi-user mode is highly experimental. DO NOT EXPOSE IT TO THE INTERNET.")
def fix_loader_name(name):
name = name.lower()
if name in ['llamacpp', 'llama.cpp', 'llama-cpp', 'llama cpp']:
return 'llama.cpp'
if name in ['llamacpp_hf', 'llama.cpp_hf', 'llama-cpp-hf', 'llamacpp-hf', 'llama.cpp-hf']:
return 'llamacpp_HF'
elif name in ['transformers', 'huggingface', 'hf', 'hugging_face', 'hugging face']:
return 'Transformers'
elif name in ['autogptq', 'auto-gptq', 'auto_gptq', 'auto gptq']:
return 'AutoGPTQ'
elif name in ['gptq-for-llama', 'gptqforllama', 'gptqllama', 'gptq for llama', 'gptq_for_llama']:
return 'GPTQ-for-LLaMa'
elif name in ['exllama', 'ex-llama', 'ex_llama', 'exlama']:
return 'ExLlama'
elif name in ['exllama-hf', 'exllama_hf', 'exllama hf', 'ex-llama-hf', 'ex_llama_hf']:
return 'ExLlama_HF'
if args.loader is not None:
args.loader = fix_loader_name(args.loader)
def add_extension(name):
if args.extensions is None:
args.extensions = [name]
elif 'api' not in args.extensions:
args.extensions.append(name)
# Activating the API extension
if args.api or args.public_api:
add_extension('api')
# Activating the multimodal extension
if args.multimodal_pipeline is not None:
add_extension('multimodal')
def is_chat():
return args.chat
def get_mode():
if args.chat:
return 'chat'
elif args.notebook:
return 'notebook'
else:
return 'default'
# Loading model-specific settings
with Path(f'{args.model_dir}/config.yaml') as p:
if p.exists():
model_config = yaml.safe_load(open(p, 'r').read())
else:
model_config = {}
# Applying user-defined model settings
with Path(f'{args.model_dir}/config-user.yaml') as p:
if p.exists():
user_config = yaml.safe_load(open(p, 'r').read())
for k in user_config:
if k in model_config:
model_config[k].update(user_config[k])
else:
model_config[k] = user_config[k]
model_config = OrderedDict(model_config)
|