Showing 1-8 of 8 projects
A distributed system for running large language models (LLMs) on personal devices, enabling faster fine-tuning and inference.
An accelerator for local LLM inference and fine-tuning on Intel XPUs, with seamless integration into popular LLM frameworks.
Firefly is a comprehensive toolkit for training large language models like Qwen, Llama, Baichuan, and more, targeting AI-focused developers.
A terminal-based interface for interacting with large language models
Run Mixtral-8x7B language models on Colab or consumer desktops with offloading capabilities.
A Mac app for Ollama, a platform for developers focused on building with AI tools and prompts.
This is a large language model (LLM) focused on mental health, with pre/post-training, datasets, evaluation, and deployment tools.
A versatile AI chat Telegram bot that leverages GPT-5, DALL·E, Groq, Gemini, and Claude APIs for web search and generation.
Get weekly updates on trending AI coding tools and projects.