Model Farm Preview User Guide

Introduction

Model Farm actively adapts to current cutting-edge or popular AI models. To help developers understand Model Farm's model adaptation and release plans as well as related model performance parameters in advance, we have launched Model Farm Preview.

Model Farm Preview uses the same methods as Model Farm with unified interface interaction. Developers can quickly view performance parameters of models that will be released in Model Farm, or contact APLUX for support to obtain related model files and inference code in advance.

💡Note

Model Farm Preview is only for viewing model adaptation status and related performance parameters. It cannot be downloaded or used. You need to wait for the model to be officially released before downloading and using it in Model Farm.

System Dependency Configuration

Configure AidLux Dependencies

# Download the correct public key
sudo wget -O- https://archive.aidlux.com/ubuntu24/public.key | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/private-aidlux.gpg > /dev/null

# Edit source file
sudo vim /etc/apt/sources.list.d/private-aidlux.list

# Fill in the private key provided by AidLux in the source file
deb [arch=arm64 signed-by=/etc/apt/trusted.gpg.d/private-aidlux.gpg] https://archive.aidlux.com/ubuntu24 noble main

# Update cache
sudo apt update

After the update is complete, you can obtain the official AidLux SDK dependencies through the following command:

sudo apt list | grep aid | grep unknown

# Install software
# Must be installed first, not included in the system
sudo apt install python3 python3-pip libopencv-dev python3-opencv  net-tools
# Must be installed before aidlite
sudo apt install aidlux-aistack-base aidrtcm

# Install aidlite and dependencies 
sudo apt install aid-lms aidlms-sdk aidlite-sdk cmake
sudo apt-get install libfmt-dev nlohmann-json3-dev
sudo apt install aidlite-*

# Support DSP
sudo apt-get install qcom-fastrpc1
sudo apt-get install qcom-fastrpc-dev

# Install aidgen-sdk
sudo apt install aidgen-sdk

# Install mms service
sudo apt install aid-mms

# Support GPU
sudo add-apt-repository ppa:ubuntu-qcom-iot/qcom-noble-ppa
sudo apt install qcom-adreno-cl1
sudo ln -s /usr/lib/aarch64-linux-gnu/libOpenCL.so.1 /usr/lib/aarch64-linux-gnu/libOpenCL.so

After installation, check the system /usr/local/share for the newly added aidlite and aidgen directories.

Device Authorization

Obtain Device SN Code

cat  /sys/devices/soc0/serial_number

Obtain Authorization File

Provide the SN number to AidLux technical personnel to generate a device-specific License file, and place it in the path /etc/opt/aidlux/license/AidLuxLics.

Quick Start

Model Farm Preview is only for previewing model performance parameters and cannot be downloaded, so developers can access all information on this page without login.

Accessing Model Farm Preview

• Developers can directly access the Model Farm Preview interface by clicking the link: Model Farm Preview

• Developers can also enter the Model Farm Preview interface through Model Farm interface interaction:

Viewing Models

Developers can search for models on Model Farm Preview according to their needs and understand detailed model information to make quick evaluations.

Model Farm Preview provides multiple ways to filter and search for models:

• Filter by model type
• Filter by model data precision
• Filter by chip platform
• Keyword search

Model Performance Reference

The model details page of Model Farm Preview provides actual performance measurements of AI models on corresponding hardware:

• Device: Development board model and corresponding chip model used for model testing
• AI Framework: Framework and version number used for model conversion and inference
• Model Data Precision: Data precision used by the converted model
• Inference Time: Actual measured runtime of the model, excluding pre/post-processing
• Precision Loss: Cosine similarity between the output matrices of the source model (FP32) and the converted model
• Model Size: File size of the converted model

💡Note

For the same SoC chip, model performance on devices with different hardware specifications should only be used as reference data

Taking SigLIP-so400m on MeiG SNM972 (QCS8550) as an example:

Access to Model Files and Code

Models in the Preview Section of the Model Farm cannot be downloaded directly via the web interface. Developers can download these assets on APLUX boards using the mms command-line tool.

The following example demonstrates how to retrieve the MobileClip2-S3 model.

1. Login via mms

Run the following command and enter your credentials:

mms login

# Enter your username: 
# Enter your password:

# A successful login will return:
# Login successfully.

2. Search for Models

Use the mms list command to search for models (supports keyword filtering):

mms list mobileclip

# Expected output:
Model           Precision  Chipset           Backend
-----           ---------  -------           -------
MobileClip-S2   FP16       Qualcomm QCS8550  QNN2.31
MobileClip2-S3  FP16       Qualcomm QCS8550  QNN2.36

3. Download MobileClip2-S3

Specify the model details using the flags below:

# -m: Model Name
# -p: Precision
# -c: Chipset
# -b: QNN Version
mms get -m MobileClip2-S3 -p fp16 -c qcs8550 -b qnn2.36

# Model assets are downloaded by default to: /var/opt/modelfarm_models