从 0 训练大模型，单卡训练一个 200M 参数模型的全流程（train a 200M‑parameter model from scratch）
☆62Sep 23, 2026Updated 3 weeks ago
Alternatives and similar repositories for miniLLM
Users that are interested in miniLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 给 Codex 全局记忆定期减负的 skill：检测重复、清理过期线程、压缩冗长表达、添加自定义全局规则 / A skill that puts Codex global memory on a periodic diet: dedupe, prune, compress,…☆101Aug 25, 2026Updated last month
- ☆92Updated this week
- Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn check…☆172Updated this week
- A desktop app for autonomous AI digital employees — with an offline-first local knowledge base and an extensible plugin ecosystem.☆227Updated this week
- ☆820Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- 几个 AI 终端开着，谁在等你一眼能看见。Claude Code、Codex 还在原来的终端里，旁边就能改文件、看 Git。macOS 本地工作台。☆197Oct 2, 2026Updated 2 weeks ago
- [LIBERO-MAX] A paired benchmark for robot-policy robustness to controlled changes introduced during execution.☆251Updated this week
- ☆107Sep 24, 2026Updated 3 weeks ago
- ☆101Updated this week
- MoLA Unified Human Motion Pretraining☆200Jul 13, 2026Updated 3 months ago
- Context compression for MCP. Same upstream call, exact results recoverable.☆186Aug 14, 2026Updated 2 months ago
- Flatkey media generation CLI for images, videos, audio, text, credits, and model discovery.☆911Updated this week
- WebInsight - 智能数据分析平台: 任意站点, 从可采判定到洞察报告 (四维合规/反爬对抗/验证码链/签名逆向/MCP 原生)☆101Sep 30, 2026Updated 2 weeks ago
- MC CityGen: Turn your own Minecraft builds into an entire city.☆388Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Source-aware China inbound travel data, CLI, HTTP API, and MCP server☆194Aug 25, 2026Updated last month
- Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-…☆1,006Updated this week
- Policy Optimization for Generative Models: diffusion and flow policies, online fine-tuning, and inference-time guidance and planning.☆101Oct 1, 2026Updated 2 weeks ago
- 🧠 NeuroConscious Transformer (NCT) - A next-generation neuromorphic consciousness architecture integrating Transformer with Global Works…☆468Aug 1, 2026Updated 2 months ago
- Verify BibTeX references against OpenAlex & CrossRef to detect errors and AI hallucinations☆146Sep 29, 2026Updated 2 weeks ago
- Task-oriented WiFi sensing dataset catalog and standardization toolkit☆108Aug 22, 2026Updated last month
- 面向中、英、日阅读与学习的 iOS/Android 电子书阅读器，支持点按AI翻译☆111Aug 11, 2026Updated 2 months ago
- CraftStation Agent Runtime Composition System☆680Updated this week
- Operant Beta：以多模型分工、按需通信、分层审批和经验复用为核心设计，在本机组织可追溯的 Agent 协作，并通过模块化架构扩展能力。☆416Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- is a next-generation, modern, and lightweight SSH client engineered for absolute efficiency. Beyond standard terminal emulation, it acts …☆237Sep 14, 2026Updated last month
- Cross-platform DICOM viewer for CT, MRI & PET/CT with MPR, 3D, fusion, editable segmentation and local AI auto-segmentation via TotalSegm…☆300Updated this week
- EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluati…☆439Updated this week
- UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation☆88Oct 9, 2026Updated last week
- ☆176Aug 21, 2026Updated last month
- FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproduci…☆733Oct 9, 2026Updated last week
- Caddy Reverse Proxy Balancer WebUI☆406Updated this week
- We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.☆512Updated this week
- Your ultimate hub to discover, manage, and share the best AI prompts. Build your personal prompt library and collaborate with the communi…☆79Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Fish Gut Resistome Atlas and FGA-ResNet web platform☆105Aug 17, 2026Updated 2 months ago
- AI Agent 对话平台 —— 流式对话、工具调用、子 Agent 委派、定时任务，以及每一次运行的完整审计轨迹。☆47Updated this week
- ☆674Oct 8, 2026Updated last week
- ☆92Jul 27, 2026Updated 2 months ago
- A chat system based on ntfy☆497Sep 10, 2026Updated last month
- Kition brings Markdown, DataTable, WhiteBoard, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.☆507Updated this week
- MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。☆874Updated this week