model_info:
  name: anemll-meta-llama-Llama-3.2-1B-Instruct-ctx1024
  version: 0.3.4
  description: |
    Demonstarates running meta-llama-Llama-3.2-1B-Instruct on Apple Neural Engine
    Context length: 1024
    Batch size: 64
    Chunks: 1
  license: MIT
  author: Anemll
  framework: Core ML
  language: Python
  architecture: llama
  parameters:
    context_length: 1024
    batch_size: 64
    lut_embeddings: none
    lut_ffn: 6
    lut_lmhead: 6
    num_chunks: 1
    model_prefix: llama
    embeddings: llama_embeddings.mlmodelc
    lm_head: llama_lm_head_lut6.mlmodelc
    ffn: llama_FFN_PF_lut6.mlmodelc
    split_lm_head: 8