model_info:
  name: anemll-Llama-3.2-1B-FAST-iOS
  version: 0.3.0
  description: |
    Demonstarates running Meta-Llama-3.2-1B on Apple Neural Engine
    Context length: 512
    Batch size: 64
    Chunks: 1
  license: MIT
  author: Anemll
  framework: Core ML
  language: Python
  parameters:
    context_length: 512
    batch_size: 64
    lut_embeddings: 8
    lut_ffn: 4
    lut_lmhead: 8
    num_chunks: 1
    model_prefix: llama
    embeddings: llama_embeddings_lut8.mlmodelc
    lm_head: llama_lm_head_lut8.mlmodelc
    ffn: llama_FFN_PF_lut4.mlmodelc