mblt-model-zoo

What problem does it solve?

This Skill simplifies the deployment of AI models optimized for Mobilint Neural Processing Units (NPUs), allowing developers to accelerate model integration and inference with reduced effort.

Core Features & Use Cases

• Optimized AI Models: Access a curated collection of pre-trained, pre-quantized models for vision, language, and multimodal tasks.
• Preprocessing & Postprocessing Tools: Evaluate, fine-tune, and integrate models with ease using provided tools.
• Use Case: A developer seeking to integrate a computer vision model into an application could use this Skill to quickly load a ResNet50 model from the Model Zoo, perform inference on new images, and retrieve processed results.

Quick Start

To load and run the ResNet50 model from the Model Zoo, execute the following Python command:

from mblt_model_zoo.vision import MBLT_Engine
model = MBLT_Engine(model_cls="resnet50", model_type="DEFAULT", model_path="", core_mode="global8")