Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Huggingface Trl Supervised Finetuning
- Workflow:LaurentMazare Tch rs Pretrained Image Classification
- Workflow:VainF Torch Pruning Object Detection Pruning
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Cleanlab Cleanlab Classification Label Issue Detection
- Workflow:BerriAI Litellm Proxy Server Deployment
- Workflow:CarperAI Trlx ILQL Offline Training
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:Mistralai Client python Text Embeddings
- Workflow:Volcengine Verl PPO Training With Reward Model
Principles
- Principle:DataTalksClub Data engineering zoomcamp Kestra Staging Load
- Principle:Mit han lab Llm awq Vision Language Projection
- Principle:AUTOMATIC1111 Stable diffusion webui UI Component Pattern
- Principle:FlowiseAI Flowise Agentflow Node Status Monitoring
- Principle:Langgenius Dify Plugin Installation
- Principle:Teamcapybara Capybara Element Finding
- Principle:VainF Torch Pruning LLM Config Update
- Principle:Princeton nlp SimPO Dataset Loading and Mixing
- Principle:SeleniumHQ Selenium Grid Health Monitoring
- Principle:ClickHouse ClickHouse Lightweight JSON Parsing
Implementations
- Implementation:Duckdb Duckdb SKA Sort
- Implementation:Mistralai Client python Models And Files Management
- Implementation:Heibaiying BigData Notes HdfsUtils HDFS Operations
- Implementation:InternLM Lmdeploy Gemm MatrixPtr
- Implementation:Mage ai Mage ai Google Ads Sync
- Implementation:Isaac sim IsaacGymEnvs HumanoidAMPBase
- Implementation:Cohere ai Cohere python BatchesClient
- Implementation:Open compass VLMEvalKit Load Env
- Implementation:Open compass VLMEvalKit MiniMonkey
- Implementation:NVIDIA DALI Rec2idx
Heuristics
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
- Heuristic:Bitsandbytes foundation Bitsandbytes Blocksize Platform Defaults
- Heuristic:SeldonIO Seldon core Tracing Latency Tip
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
- Heuristic:Eventual Inc Daft Delta Lake S3 Locking
- Heuristic:Predibase Lorax GPU Sampling Optimization
- Heuristic:Datajuicer Data juicer Checkpoint Resumption Strategy
- Heuristic:Openai CLIP Template Ensemble For Zero Shot
- Heuristic:Speechbrain Speechbrain Score Normalization Tips
- Heuristic:Scikit learn Scikit learn Feature Scaling Numerical Stability
Environments
- Environment:Norrrrrrr lyn WAInjectBench OpenAI API Credentials
- Environment:Liu00222 Open Prompt Injection Python Dependencies
- Environment:Promptfoo Promptfoo SQLite Database
- Environment:Shiyu coder Kronos PyTorch CUDA Environment
- Environment:Protectai Llm guard Python Runtime Dependencies
- Environment:Protectai Llm guard ONNX Runtime Acceleration
- Environment:Danijar Dreamerv3 JAX CUDA
- Environment:NVIDIA DALI CMake Build Environment
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:Iterative Dvc Python Runtime