Starred repositories
视频同声传译（奇慧智译）
Implements harmful/harmless refusal removal using pure HF Transformers
A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
低成本的简单基于live2d TTS文字转语音和大模型聊天的直播解决方案
Disable/Enable Windows update with a lightweight batch tool.
The "Activate Windows" watermark ported to Linux
A Conversational Speech Generation Model
D^2-MoE: Delta Decompression for MoE-based LLMs Compression
verl: Volcano Engine Reinforcement Learning for LLMs
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
Train transformer language models with reinforcement learning.
[ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Training Large Language Model to Reason in a Continuous Latent Space
Recipes to train reward model for RLHF.
Simple frontend for LLMs built in react-native.
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
绝区零 一条龙 | 全自动 | 自动闪避 | 自动每日 | 自动空洞 | 支持手柄
VPTQ, A Flexible and Extreme low-bit quantization algorithm
Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
Build your own second brain with supermemory. Extremely fast, scalable, memory API for the AI era.