[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Large Language & Foundation Models for Time Series.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

fount (aka 豊人（ほうと）/纺铽（fǎng tè | ㄈㄤˇ ㄊㄜˋ）) is an extensible framework for building and hosting AI character interactions. Built with pure JS, offers unparalleled flexibility via modular components, …

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

A streamlined and customizable framework for efficient large model evaluation and performance benchmarking

Integrate cutting-edge LLM technology quickly and easily into your apps

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Automatically evaluate your LLMs in Google Colab

LLM inference in C/C++

Ginger is a stand-alone editor for LLM character cards.

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Roleplay with AI with a focus on strong narration, consistent world and game state tracking.