Stars
Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Tr…
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Git Server with CI/CD, Kanban, and Packages. Seamless integration. Unparalleled experience.
An elegent pytorch implement of transformers
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)
This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
MiniCPM4: Ultra-Efficient LLMs on End Devices, achieving 5+ speedup on typical end-side chips
💥 A Lodash-style Go library based on Go 1.18+ Generics (map, filter, contains, find...)
An implementation of 1D, 2D, and 3D positional encoding in Pytorch and TensorFlow
Linux virtual machines, with a focus on running containers
Stable Diffusion web UI
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
ebpf-go is a pure-Go library to read, modify and load eBPF programs and attach them to various hooks in the Linux kernel.
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
AirLLM 70B inference with single 4GB GPU
Ebitengine - A dead simple 2D game engine for Go
Golang client for NATS, the cloud native messaging system.
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
🌐 The Internet OS! Free, Open-Source, and Self-Hostable.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.