githubofhuo
Follow
Stars
High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogeneous engines and extreme memory efficiency for GRPO, PPO, etc.
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
Real-time voice + vision on Meta Ray-Ban or iPhone, with Gemini Live. OpenClaw (Alan) runs actions on your Mac — reminders, messages, share to Instagram, and more.
Seedance2 视频创意技能包：100+ 镜头词库、Seedance 2.0 全模态 API CLI，兼容 OpenClaw / Cursor / 任意 Agent 平台。AI Agent skill for ByteDance Seedance video generation. Creativity gate (memorability / surprise / emotion / …
Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models
🔥🔥🔥 Latest Papers, Codes and Datasets on Video-LMM Post-Training
Optimize QWen1.5 models with TensorRT-LLM
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Draw a mockup and generate html for it
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
An open-source, tool-augmented conversational language model from Fudan University
中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com
A cli tool to scrap user activity data from Discord.
一个简单易用的 Python 模块，用于通过字符串来操作日期/时间。正则时间提取，字符串时间解析，字符串时间提取。中文时间提取，一句话里面提取时间
An enterprise-class UI design language and React UI library
My best practice of training large dataset using PyTorch.
it's the realization of Tree-based Deep Model with tensorflow
Focus on what matters instead of fighting with Git.
🤗 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.
🌺Algorithm papers, coursewares, documents, notes and other materials are constantly being updated.
The official implementation of G-TAD: Sub-Graph Localization for Temporal Action Detection