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:Zai org CogVideo Video Captioning
- Workflow:Princeton nlp SimPO On Policy Data Generation
- Workflow:OWASP Www project top 10 for large language model applications LLM Vulnerability Assessment
- Workflow:Pola rs Polars Time Series Analysis
- Workflow:Lucidrains X transformers DPO Preference Alignment
- Workflow:Huggingface Transformers Model Benchmarking
- Workflow:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:Huggingface Alignment handbook QLoRA Single GPU Finetuning
- Workflow:Microsoft BIPIA Attack Success Rate Evaluation
- Workflow:Huggingface Alignment handbook ORPO Single Stage Alignment
Principles
- Principle:Predibase Lorax Dynamic LoRA Loading
- Principle:Iterative Dvc Vega Lite Conversion
- Principle:Wandb Weave Prompt Retrieval
- Principle:Huggingface Datasets Spark Dataset Building
- Principle:Eric mitchell Direct preference optimization Checkpoint Saving
- Principle:MaterializeInc Materialize Container Registry Publishing
- Principle:Nautechsystems Nautilus trader Strategy Shutdown
- Principle:Scikit learn Scikit learn Semi Supervised Learning
- Principle:Online ml River Online One Class SVM
- Principle:Anthropics Anthropic sdk python Streaming Thinking Content
Implementations
- Implementation:Pyro ppl Pyro AffineBeta
- Implementation:ClickHouse ClickHouse EnumReflection
- Implementation:Apache Shardingsphere ShadowOperationType Enum
- Implementation:OpenGVLab InternVL ScienceQA Inference
- Implementation:Helicone Helicone AI Gateway OpenAPI Spec
- Implementation:Facebookresearch Habitat lab Selection
- Implementation:Cohere ai Cohere python AssistantMessage Model
- Implementation:Openai CLIP Accuracy Function
- Implementation:Openai Openai node Node ESM Auto Lockfile
- Implementation:Pyro ppl Pyro Distribution Utilities
Heuristics
- Heuristic:Huggingface Trl Distributed Device Map Override
- Heuristic:Mbzuai oryx Awesome LLM Post training Reference Citation Cap 200
- Heuristic:NVIDIA DALI Batch Size Tuning
- Heuristic:Google deepmind Mujoco Thread Pool Configuration
- Heuristic:Apache Airflow Scheduler Performance Tuning
- Heuristic:Vespa engine Vespa Warning Deprecated Cloud API Constructors
- Heuristic:Langchain ai Langgraph Recursion Limit Tuning
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Online ml River Hoeffding Tree Grace Period Tuning
- Heuristic:Heibaiying BigData Notes HBase Connection Thread Safety Tip
Environments
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment
- Environment:Heibaiying BigData Notes Kafka 2 2 Environment
- Environment:Guardrails ai Guardrails Docker Server Runtime
- Environment:ClickHouse ClickHouse Systemd Runtime
- Environment:Diagram of thought Diagram of thought Python Graph Libraries
- Environment:Wandb Weave LLM Integration Dependencies
- Environment:Apache Airflow Kubernetes Helm Environment
- Environment:Avdvg InjectGuard CUDA GPU
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Infiniflow Ragflow Data Source Credentials