Class LlamaModelParams

java.lang.Object
chat.octet.model.beans.LlamaModelParams

public class LlamaModelParams extends Object
Llama model params entity
Author:
William
  • Field Details

    • gpuLayers

      public int gpuLayers
      number of layers to store in VRAM.
    • mainGpu

      public int mainGpu
      the GPU that is used for scratch and small tensors.
    • tensorSplit

      public float[] tensorSplit
      how to split layers across multiple GPUs (size: LLAMA_MAX_DEVICES).
    • vocabOnly

      public boolean vocabOnly
      only load the vocabulary, no weights.
    • mmap

      public boolean mmap
      use mmap if possible.
    • mlock

      public boolean mlock
      force system to keep model in RAM.
  • Constructor Details

    • LlamaModelParams

      public LlamaModelParams()