Janus-Series: Unified Multimodal Understanding and Generation Models
- any-to-any
- foundation-models
- llm
- multimodal
47,133 repositories indexed
25–48 of 72 · Most stars
Janus-Series: Unified Multimodal Understanding and Generation Models
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
TranslatedFay is an agent framework that helps digital humans (2.5D, 3D, mobile, PC, web) or large language models (OpenAI-compatible, DeepSeek) connect to business systems.
Minimal reproduction of DeepSeek R1-Zero
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
TranslatedOpen-source manuscript of 《深入理解 AI Infra:量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
TranslatedWorkBuddy international and domestic multi-account reverse proxy gateway, supporting Codex / Claude Code / DSH and standard OpenAI clients.
SSH server auditing (banner, key exchange, encryption, mac, compression, compatibility, security, etc)
UFONet - Denial of Service Toolkit
🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
Python Module Dependency graphs
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
When Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill.
Implementing LLM architectures from scratch in PyTorch
TranslatedOne-click replacement of the built-in prompts of three AI clients: DSH / WorkBuddy / ZCode. Double-click to use, self-verifiable, backup before changes, one-click restore. v8.29: card-style interface, activation code required to log in, automatic DSH plugin injection, official group verification. Single-file exe with no Python installation needed, completely free and open source.
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.
TranslatedDeepSeek Harness integrated armor-breaking security analysis plugin: aggregating all domains of Android · Web · Native · Protocol · Malware · AI-Security (9 bundles + 1 preset)
Train and Deploy an ML REST API to predict crypto prices, in 10 steps
TranslatedNot a Q&A bot, but a digital twin that can actually get work done. Agents and project context are shared, so all project members can work together. At the same time, agents, like people, abstract and summarize experience from materials or work into the project context.
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts