AI
QLoRA: Efficient Finetuning of Quantized LLMs
Blender addon to inspect and preprocess COLMAP data for Neuralangelo (CVPR 2023)
A latent text-to-image diffusion model
Hackable and optimized Transformers building blocks, supporting a composable construction.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
The official gpt4free repository | various collection of powerful language models | o4, o3 and deepseek r1, gpt-4.1, gemini 2.5
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
An arbitrary face-swapping framework on images and videos with one single trained model!
DeepFaceLab is the leading software for creating deepfakes.
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
An open-source tool-augmented conversational language model from Fudan University
骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech