model_info:
  name: anemll-google-gemma-3-1b-it-ctx4096
  version: 0.3.5
  description: |
    Demonstarates running google-gemma-3-1b-it on Apple Neural Engine
    Context length: 4096
    Batch size: 64
    Chunks: 1
  license: MIT
  author: Anemll
  framework: Core ML
  language: Python
  architecture: gemma3_text
  parameters:
    context_length: 4096
    batch_size: 64
    lut_embeddings: 6
    lut_ffn: 6
    lut_lmhead: 6
    num_chunks: 1
    model_prefix: gemma3
    embeddings: gemma3_embeddings_lut6.mlmodelc
    lm_head: gemma3_lm_head_lut6.mlmodelc
    ffn: gemma3_FFN_PF_lut6_chunk_01of01.mlmodelc
    split_lm_head: 16
    vocab_size: 262144
    lm_head_chunk_sizes: [16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]
    sliding_window: 512
    prefill_dynamic_slice: true

# =============================================================================
# Conversion Parameters (for troubleshooting)
# =============================================================================
# Generated: 2026-04-19 11:44:03
#
# model_path: /Users/optai/.cache/huggingface/hub/models--google--gemma-3-1b-it/snapshots/dcc83ea841ab6100d6b47a070329e1ba4cf78752
# output_dir: /Users/optai/Desktop/npubench/Anemll/gemma3_1b_lut6_ctx4096
# command_line: ./anemll/utils/convert_model.sh --model google/gemma-3-1b-it --output ./gemma3_1b_lut6_ctx4096 --context 4096 --batch 64 --lut1 6 --lut2 6 --lut3 6 --chunk 1
# context_length: 4096
# batch_size: 64
# num_chunks: 1
# lut_part1: 6
# lut_part2: 6
# lut_part3: 6
# prefix: gemma3
# architecture: gemma3_text
# argmax_in_model: false
# split_rotate: false
# sliding_window: 512
# single_cache: false
# dynamic_prefill_slice: true
# monolithic: false
# anemll_version: 0.3.5
# vocab_size: 262144
# lm_head_chunk_sizes: "[16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384, 16384]"
# =============================================================================