Namespace LMKit.Model

Classes

LM

Manages language model instances, supporting both Small Language Models (SLMs) and Large Language Models (LLMs) in GGUF and LMK formats. This class facilitates loading, configuring, and interacting with various language models within the LM-Kit library, ensuring compatibility and streamlined operations across different model sizes and formats.

LM.DeviceConfiguration

Handles the underlying model device configuration, including GPU settings and memory management options.

LM.LoadingOptions

Represents options for loading a model, allowing customization of the loading process.

LM.Metadata

Represents metadata information associated with a model.

LM.MetadataCollection

Represents a collection of Metadata objects.

LM.TensorDistribution

Represents the distribution of model layers or rows across multiple GPUs.

ModelCard

Represents metadata and attributes for a language model in the LM-Kit library.

Enums

LM.Precision

Represents the different precision types for LM models.

LM.RopeType

Specifies the type of rope algorithm used for positional encoding in models.

LM.TemplateFormat

Defines the possible formats for model chat templates, indicating specific structures and encoding standards used for chatbot interactions.

LM.TemplateFormatFlags

Specifies flags that control how template formats handle system messages and suffixes when generating prompts for language models.

ModelCapabilities

Represents the various purposes a model can serve in the LM-Kit library. The Flags attribute allows combining multiple capabilities using bitwise operations.

Delegates

LM.ModelDownloadingProgressCallback

A delegate designed to monitor and report the progress of model downloading.

LM.ModelLoadingProgressCallback

A delegate designed to monitor and report the progress of model loading.