Buy me a coffee if you like this project ;)

GGUF Format model files for This project.

GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:

Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information. Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models. mmap compatibility: models can be loaded using mmap for fast loading and saving. Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used. Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user. The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for inference or for identifying the model.

User: Tell me story about what is an quantization and what do we need to build.

Assistant: Quantization is a process used in signal processing, physics, and mathematics to convert continuous signals or data into discrete values. It's often used in digital systems to represent analog signals or phenomena, allowing for efficient storage, transmission, and processing of information. In the context of audio, video, or images, quantization converts the infinite range of possible signal values into a finite number of levels that can be represented using a certain number of bits.

To understand this better, let's consider an example with audio. Sound waves are continuous signals, and when we record them, we need to