baby-llama2-chinese
A repo for pretraining and SFT of a small Chinese LLaMA2 from scratch; a single 24GB GPU is enough to produce a chat-LLaMA2 capable of simple Chinese Q&A.
HYSEN LABS DIRECTORY
Curated AI & Machine Learning repositories with precise tags and practical analysis.
A repo for pretraining and SFT of a small Chinese LLaMA2 from scratch; a single 24GB GPU is enough to produce a chat-LLaMA2 capable of simple Chinese Q&A.
Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time
Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
Project brief: 471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.
Ideogram 4: Open image model at the forefront of design
The context orchestration layer powered by hypergraphs. Build a unified semantic context layer where agentic outcomes are deterministic and agent behavior is not just traceable, but cryptographically verifiable.
An Android system-level AI agent that bypasses the sandbox, giving the model access to low-level APIs, the screen, the terminal and your data.
Jessibuca is an open-source pure-H5 live stream player.
Learn how to get started using the GitHub Copilot CLI!
Design and implement web animations that respond to scroll, drag, pointer, or state changes, covering assets, timelines, and runtime.
Beautiful git diff viewer, generate commits with AI, get summary of changes, all from the CLI
Implementation of papers in 100 lines of code.
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
A professional video compression tool accessible to all, mostly based on FFmpeg.
Give Claude Code a subconscious
An unofficial rules engine for the world's greatest card game.
IntelliJ IDEA plugin that automatically generates Javadoc comments.
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.
Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark.
Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual dashboard, remote proxy support, WebSearch fallback. Zero-config to production-ready.