anemll's picture
Upload folder using huggingface_hub
a9469a5 verified
raw
history blame
439 Bytes
model_info:
name: anemll-Meta-Llama-3.2-3B-ctx512
version: 0.1.1
description: |
Demonstarates running Meta-Llama-3.2-3B on Apple Neural Engine
Context length: 512
Batch size: 64
Chunks: 2
license: MIT
author: Anemll
framework: Core ML
language: Python
parameters:
context_length: 512
batch_size: 64
lut_embeddings: none
lut_ffn: 4
lut_lmhead: 4
num_chunks: 2
model_prefix: llama