This is a Llama-3.2 1B Instruct model converted to an Anemll model using Anemll 0.1.2 and with the context size set to 1024 (cannot be changed at runtime).
It was converted using the convert_model.sh script
and a --context 1024 parameter.
Some things ⬇️
Anemll is in alpha, proceed at your own risk.
You will need to clone the Anemll repo to run this model (unlike the Anemll HF models that include runnable chat.py files).
Once you've downloaded both this model and the Anemll repo you can either follow the chat instructions from the docs or run it using
Anemll models can only be ran with the Anemll library and on Apple silicon. DYOR if this model is for you or not. The Anemll library creators are active on X.
Below is the copy pasted README from one of the original HF Anemll models. Follow the instructions untill the run part, where instead of running a chat.py file that does not exist in this repo, you will run a chat.py file from the cloned Anemll repo (see above).
ANEMLL (pronounced like "animal") is an open-source project focused on accelerating the porting of Large Language Models (LLMs) to tensor processors, starting with the Apple Neural Engine (ANE).
The goal is to provide a fully open-source pipeline from model conversion to inference for common LLM architectures running on ANE.
This enables seamless integration and on-device inference for low-power applications on edge devices, ensuring maximum privacy and security.
This is critical for autonomous applications, where models run directly on the device without requiring an internet connection.
License
ANEMLL is licensed under the MIT License.
The model is based on Meta's LLaMA 3.2 and may require a separate license.
This test model is exclusively for the Meta's LLaMA 3.2 1B (512 context) model converted for CoreML, released before the official launch of the ANEMLL repository and minimal documentation. It is intended for early adopters only who requested an early release.
Requirements
macOS Sequoia with Apple Neural Engine and 16GB RAM
CoreML Tools and HuggingFace Transformers libraries
Python 3.9
chat.py provides a sample inference script. chat_full.py provides a sample inference script with history and conversation management.
Installation
Download the model from Hugging Face:
bash
1# Install required tools2pip install huggingface_hub
34# Install Git LFS (Large File Support)5# macOS with Homebrew:6brew install git-lfs
7# Or Ubuntu/Debian:8# sudo apt-get install git-lfs910# Initialize Git LFS11git lfs install1213# Clone the repository with model files14git clone https://huggingface.co/anemll/anemll-Meta-Llama-3.2-1B-ctx512_0.1.1
Extract model files:
bash
1# Navigate to cloned directory2cd anemll-Meta-Llama-3.2-1B-ctx512_0.1.1
34# Pull LFS files (model weights)5git lfs pull
67# Extract CoreML model files8find. -type f -name "*.zip" -exec unzip{}\;
Note: The first time the model loads, macOS will take some time to place it on the device.
Subsequent loads will be instantaneous.
Use Ctrl-D to exit, Ctrl-C to interrupt inference.
More InfoMore Info
Please check following links for later updates:
