Stars
Natural Language Processing in Ethiopian Languages: Current State, Challenges, and Opportunities
Code and documentation to train Stanford's Alpaca models, and generate the data.
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
Lets Git started in the world of opensource, starting in the Zero To Mastery's opensource playground. Especially designed for education and practical experience purposes.
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
An example starter repo for Python projects
Lacuna funded project to create benchmark dataset for AfricaNLI, AfricaMGSM, AfricaMMLU, and cultural relevant intent classificationand slot filling detection datasets
South-East Asia Large Language Models
Blueprint by Mozilla.ai for finetuning a Speech-To-Text model in your own language
Model Context Protocol Servers
Composable building blocks to build Llama Apps
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses XTTS, OpenAI, ElevenLabs or Kokoro
A User Interface for XTTS-2 Text-Based Voice Cloning using only 10 seconds of speech
Inference and training library for high-quality TTS models.
A list of scripts/notebooks I'd like to keep handy
Hub des projets initiés par GalsenAI
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.