parser.add_argument("-s", "--seed", type=int, default=-1, help="RNG seed (use random seed for <= 0)",dest="seed")
parser.add_argument("-t", "--threads", type=int, default=min(4, os.cpu_count() or1), help="number of threads to use during computation",dest="n_threads")
parser.add_argument("-n", "--n_predict", type=int, default=128, help="number of tokens to predict (-1 = infinity)",dest="n_predict")
parser.add_argument("--n_parts", type=int, default=-1, help="number of model parts", dest="n_parts")
parser.add_argument("-c", "--ctx_size", type=int, default=512, help="size of the prompt context",dest="n_ctx")
parser.add_argument("-b", "--batch_size", type=int, default=8, help="batch size for prompt processing",dest="n_batch")
parser.add_argument("--keep", type=int, default=0, help="number of tokens to keep from the initial prompt",dest="n_keep")
parser.add_argument(
"-l",
"--logit-bias",
type=str,
action='append',
help="--logit-bias TOKEN_ID(+/-)BIAS",
dest="logit_bias_str"
)
parser.add_argument("--ignore-eos", action="store_true", help="ignore end of stream token and continue generating", dest="ignore_eos")
parser.add_argument("--mirostat_ent", type=float, default=5.0, help="Mirostat target entropy, parameter tau represents the average surprise value",dest="mirostat_tau")
parser.add_argument("--lora-base", type=str, default="", help="optional model to use as a base for the layers modified by the LoRA adapter", dest="lora_base")
parser.add_argument("--memory_f32", action="store_false", help="use f32 instead of f16 for memory key+value",dest="memory_f16")
parser.add_argument("--random-prompt", action="store_true", help="start with a randomized prompt.", dest="random_prompt")
parser.add_argument(
"--color",
action="store_true",
help="colorise output to distinguish prompt and user input from generations",
dest="use_color"
)
parser.add_argument(
"-i", "--interactive", action="store_true", help="run in interactive mode", dest="interactive"
help="run in interactive mode and wait for input right away",
dest="interactive_start"
)
parser.add_argument(
"-ins",
"--instruct",
action="store_true",
help="run in instruction mode (use with Alpaca or Vicuna models)",
dest="instruct"
)
parser.add_argument("--no-penalize-nl", action="store_false", help="do not penalize newline token", dest="penalize_nl")
parser.add_argument("--perplexity", action="store_true", help="compute perplexity over the prompt", dest="perplexity")
parser.add_argument("--no-mmap", action="store_false",help="do not memory-map model (slower load but may reduce pageouts if not using mlock)",dest="use_mmap")
parser.add_argument("--mlock", action="store_true",help="force system to keep model in RAM rather than swapping or compressing",dest="use_mlock")
parser.add_argument("--mtest", action="store_true",help="compute maximum memory usage",dest="mem_test")
parser.add_argument("--verbose-prompt", action="store_true",help="print prompt before generation",dest="verbose_prompt")
#Custom args
parser.add_argument("--fix-prefix", type=str, default="", help="append to input when generated n_predict tokens", dest="fix_prefix")
parser.add_argument("--input-noecho", action="store_false", help="dont output the input", dest="input_echo")