README.md

Explore Arm-Optimized Learning Paths on Hugging Face

Arm’s AI development resources ensure you can deploy at pace, achieving best performance on Arm by default. Our aim is to make your AI development easier, ensuring integration with all major operating systems and AI frameworks, enabling portability for deploying AI on Arm at scale.

Discover curated Learning Paths that showcase AI models optimized for Arm platforms across key market applications. Each learning path highlights specific models featured within our dedicated Hugging Face Model Collections, simplifying your journey from learning to deployment on Arm technologies.

Learning Path	Market Application	Model(s) Featured
CV: Image Classification & Object Detection
Profile the Performance of AI and ML Mobile Applications on Arm	Smartphone	Mobilenet V2 1.0 224
Run a Computer Vision Model on a Himax Microcontroller	IoT	CV: Image Classification & Object Detection	Ultralytics
Get started with object detection using a Jetson Orin Nano	IoT	CV: Image Classification & Object Detection	Mobilenet V2 1.0 224
GenAI: RAG
Build a RAG application using Zilliz Cloud on Arm servers	Cloud & Datacenter	GenAI: RAG	All Minilm L6 V2
Build a RAG application using Zilliz Cloud on Arm servers	Cloud & Datacenter	GenAI: RAG	Dolphin 2.9.4 Llama3.1 8B Gguf
GenAI: Text Generation
Deploy a Large Language Model (LLM) chatbot with llama.cpp using KleidiAI on Arm servers	Cloud & Datacenter	GenAI: Text Generation	Dolphin 2.9.4 Llama3.1 8B Gguf
Run a Large Language Model (LLM) chatbot with PyTorch using KleidiAI on Arm servers	Cloud & Datacenter	GenAI: Text Generation	Llama 3.1 8B Instruct
Deploy a RAG-based Chatbot with llama-cpp-python using KleidiAI on Google Axion processors	Cloud & Datacenter	GenAI: Text Generation	Llama3.1 8B Gguf
Build an Android chat app with Llama, KleidiAI, ExecuTorch, and XNNPACK	Smartphone	GenAI: Text Generation	Llama 3.2 1B Instruct
Run a local LLM chatbot on a Raspberry Pi 5	Raspberry Pi	GenAI: Text Generation	Orca Mini 3B Gguf
Build an Android chat application with ONNX Runtime API	Smartphone	GenAI: Text Generation	Phi 3 Vision 128K Instruct Onnx Cuda
Run an LLM chatbot with rtp-llm on Arm-based servers	Cloud & Datacenter	GenAI: Text Generation	Qwen2 0.5B Instruct
Build and Run a Virtual Large Language Model (vLLM) on Arm Servers	Cloud & Datacenter	GenAI: Text Generation	Qwen2.5 0.5B Instruct
LLM inference on Android with KleidiAI, MediaPipe, and XNNPACK	Smartphone	GenAI: Text Generation	Gemma 2B
Run Llama 3 on a Raspberry Pi 5 using ExecuTorch	Raspberry Pi	GenAI: Text Generation	Llama 3.1 8B
Sentiment Analysis
Accelerate NLP models from Hugging Face on Arm servers	Cloud & Datacenter	Sentiment Analysis	Distilbert Base Uncased Finetuned Sst 2 English
Run a Natural Language Processing (NLP) model from Hugging Face on Arm servers	Cloud & Datacenter	Sentiment Analysis	Twitter Roberta Base Sentiment Latest

Arm Kleidi: Unleashing Mass-Market AI Performance on Arm

Arm Kleidi is a targeted software suite, expediting optimizations for any framework and enabling accelerations for billions of AI workloads across Arm-based devices everywhere. Application developers achieve top performance by default, with no additional work or investment in new skills or tools training required.

Useful Resources on Arm Kleidi:

• Arm KleidiAI for optimizing any AI framework: Gitlab repo and blog
• Arm KleidiCV for optimizing any computer vision framework: Gitlab repo and blog
• Arm Compute Library for all AI software

Note: The data collated here is sourced from Arm and third parties. While Arm uses reasonable efforts to keep this information accurate, Arm does not warrant (express or implied) or provide any guarantee of data correctness due to the ever-evolving AI and software landscape. Any links to third-party sites and resources are provided for ease and convenience. Your use of such third-party sites and resources is subject to the third party’s terms of use, and use is at your own risk.