Ready-to-assemble AI

At Flatpack, our mission is clear: we are committed to building trust in AI.

Flatpack democratises AI and ML through micro language models and model compression. Our platform enables users to train custom language models with 100M to 10B parameters. We introduce flatpacks (FPKs) to integrate AI and ML into edge computing, electronic components, and robots.

github.com/RomlinGroup/Flatpack

Sandbox

amd-llama

bark-local

euro-llm

flux-1-schnell

llama-cpp

llm-c

mediapipe

minicpm-llama3

minicpm-s-1b

moondream

nanogpt

yi-coder

Micro language models

Micro language models with around 100M to 10B parameters, offer a compelling alternative to the deployment and scalability challenges associated with traditional large language models (LLMs).

Model compression

Model compression reduces model sizes, improving efficiency while cutting energy consumption and emissions, making it an essential part of our flatpacks.

Output Guard

Output Guard (under development) secures AI model outputs. It ensures content quality and regulatory compliance, enabling confident AI adoption across industries.