LlamaCppModelParameters Configuration

LlamaCppModelParameters(name: str, provider: str = 'llama.cpp', verbose: Optional[bool] = False, concurrency: Optional[int] = 5, backend: Optional[str] = None, prompt_template: Optional[str] = None, context_length: Optional[int] = None, reasoning_model: Optional[bool] = None, path: Optional[str] = None, device: Optional[str] = None, seed: Optional[int] = -1, n_threads: Optional[int] = None, n_batch: Optional[int] = 512, n_gpu_layers: Optional[int] = 1000000000, n_gqa: Optional[int] = None, rms_norm_eps: Optional[float] = 5e-06, cache_capacity: Optional[str] = None, prefer_cpu: Optional[bool] = False)

Parameters

Name	Type	Required	Description
name	string	✅	The name of the model.
path	string	❌	The path of the model, if you want to deploy a local model.
backend	string	❌	The real model name to pass to the provider, default is None. If backend is None, use name as the real model name.
device	string	❌	Device to run model. If None, the device is automatically determined
provider	string	❌	The provider of the model. If model is deployed in local, this is the inference type. If model is deployed in third-party service, this is platform name('proxy/<platform>') Defaults：llama.cpp
verbose	boolean	❌	Show verbose output. Defaults：False
concurrency	integer	❌	Model concurrency limit Defaults：5
prompt_template	string	❌	Prompt template. If None, the prompt template is automatically determined from model. Just for local deployment.
context_length	integer	❌	The context length of the model. If None, it is automatically determined from model.
reasoning_model	boolean	❌	Whether the model is a reasoning model. If None, it is automatically determined from model.
seed	integer	❌	Random seed for llama-cpp models. -1 for random Defaults：-1
n_threads	integer	❌	Number of threads to use. If None, the number of threads is automatically determined
n_batch	integer	❌	Maximum number of prompt tokens to batch together when calling llama_eval Defaults：512
n_gpu_layers	integer	❌	Number of layers to offload to the GPU, Set this to 1000000000 to offload all layers to the GPU. Defaults：1000000000
n_gqa	integer	❌	Grouped-query attention. Must be 8 for llama-2 70b.
rms_norm_eps	number	❌	5e-6 is a good value for llama-2 models. Defaults：5e-06
cache_capacity	string	❌	Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.
prefer_cpu	boolean	❌	If a GPU is available, it will be preferred by default, unless prefer_cpu=False is configured. Defaults：False