Content | Mozilla.ai

Content

Blueprints

Blueprints is a Mozilla AI initiative helping developers get started with building open-source AI solutions.

This blueprint introduces an approach to personal, local timeline algorithms that people can either run out-of-the-box or customize.

Blueprints

Finetune an LLM using Federated AI

This Blueprint demonstrates how to finetune LLMs using federated AI with Flower, enabling collaboration on private datasets without sharing raw data

Tools

Trusted open-source tools to assist you in building AI solutions.

All Tools

Tools

OuteTTS

OuteTTS is an package for using OuteTTS text-to-speech models.

Tools

Streamlit

Streamlit is an open-source Python framework for creating interactive data applications effortlessly.

Tools

Mastodon.py

Mastodon is a free, decentralized, and open-source social network designed to give users control over their online experience.

Tools

Marimo

Marimo is an open-source reactive notebook for Python that keeps your code and outputs always in sync

Datasets

Vetted open-source datasets to assist you in building AI solutions.

All Datasets

Datasets

Common Voice

A multilingual, crowdsourced collection of voice recordings from Mozilla.

Datasets

Alpaca-gpt4

This dataset contains English Instruction-Following generated by GPT-4 using Alpaca prompts for fine-tuning LLMs.

Models

Recommended open-source datasets to assist you in building AI solutions.

All Models

Models

OuteTTS-0.1-350M

OuteTTS-0.1-350M is a novel text-to-speech synthesis model.

Models

Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters.

Content

The latest open-source content related to Blueprints, Tools, Datasets and Models.

All Content

Resources

Attend the Flower AI Summit

Join the federated AI community.

Resources

Comparing RAG, Long-Context Models, and Lightweight Alternatives

Articles that played a key-role in shaping the ideas and approaches behind this Blueprint.

Mozilla.ai

No results found.

Please try another filter combination.

Blueprints

Blueprints are a Mozilla AI initiative helping developers get started with building open-source AI solutions.

Explore All Blueprints

Blueprints

Fetch Posts & Generate Embeddings with LLM

Personalized Timeline

Build Your Own Timeline Algorithm

This blueprint introduces an approach to personal, local timeline algorithms that people can either run out-of-the-box or customize.

Blueprints

Federated AI

LLM

Finetune an LLM using Federated AI

This Blueprint demonstrates how to finetune LLMs using federated AI with Flower, enabling collaboration on private datasets without sharing raw data

Blueprints

CompVis

Map Features

Map Features in OpenStreetMap with Computer Vision

This Blueprint shows you how to fine-tune an object detection model to map features in OpenStreetMap, with human verification.

Blueprints

Speech

Document

Finetune a speech recognition model for your voice

This Blueprint demonstrates how to fine-tune a Speech-To-Text model in your own language using CommonVoice data and your own voice data.

Blueprints

Document

Q&A

Query structured documents using a lightweight LLM workflow

This Blueprint demonstrates how to use open-source models and a simple LLM workflow to answer questions based on structured documents.

Blueprints

Document

Podcast

Create your own tailored podcast using your documents

This blueprint demonstrates how you can use open-source models & tools to convert input documents into a podcast featuring two speakers.

Tools

Trusted open-source tools to assist you in building AI solutions.

Explore All Tools

Tools

OuteTTS

OuteTTS is an package for using OuteTTS text-to-speech models.

Tools

Streamlit

Streamlit is an open-source Python framework for creating interactive data applications effortlessly.

Tools

Mastodon.py

Mastodon is a free, decentralized, and open-source social network designed to give users control over their online experience.

Tools

Marimo

Marimo is an open-source reactive notebook for Python that keeps your code and outputs always in sync

Tools

Gradio

Gradio allows you to build a friendly web interface so that anyone can use your project.

Tools

HuggingFace Hub

The huggingface_hub library is used to interact with the HuggingFace Hub, enabling you to discover pre-trained models and datasets for your projects.

Tools

HuggingFace Transformers

HuggingFace Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.

Tools

Flower

Flower is a customizable, extendable, and framework-agnostic framework for building federated learning systems.

Tools

Llamafile

Llamafile allows you to run local LLMs efficiently and easily.

Tools

Kokoro

Kokoro is an inference library for the Kokoro model, an open-weight TTS model.

Tools

SAM 2

The Segment Anything Model 2 (SAM 2) is an advanced AI model developed by Meta AI, designed to perform real-time, promptable object segmentation in both images and videos.

Tools

Ultralytics

Ultralytics provides cutting-edge computer vision models, including YOLO11, enabling developers to integrate real-time object detection, segmentation, and classification into AI applications with minimal effort.

Tools

PyMuPDF

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Tools

Llama.cpp

Enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware

Datasets

Vetted open-source datasets to assist you in building AI solutions.

Explore All Datasets

Datasets

Common Voice

A multilingual, crowdsourced collection of voice recordings from Mozilla.

Datasets

Alpaca-gpt4

This dataset contains English Instruction-Following generated by GPT-4 using Alpaca prompts for fine-tuning LLMs.

Models

Recommended open-source models to assist you in building AI solutions.

Explore All Models

Models

OuteTTS-0.1-350M

OuteTTS-0.1-350M is a novel text-to-speech synthesis model.

Models

Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters.

Models

Qwen2.5-3B-Instruct-GGUF

Qwen2.5-3B-Instruct-GGUF is an instruction-tuned model that generates long-form content, and is optimized for efficient deployment via the GGUF format.

Content

The latest open-source content related to Blueprints, Tools, Datasets and Models.

Resources

Attend the Flower AI Summit

Join the federated AI community.

Resources

Comparing RAG, Long-Context Models, and Lightweight Alternatives

Articles that played a key-role in shaping the ideas and approaches behind this Blueprint.

Mozilla.ai

Resources