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:Haotian liu LLaVA LoRA Finetuning
- Workflow:FlagOpen FlagEmbedding Embedder Finetuning
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:Googleapis Python genai Model Fine Tuning
- Workflow:Ggml org Llama cpp HF to GGUF Model Conversion
- Workflow:ArroyoSystems Arroyo UDF Development
- Workflow:Rapidsai Cuml GPU Clustering
- Workflow:Mlflow Mlflow Model Serving
- Workflow:SeldonIO Seldon core Model Deployment
- Workflow:Protectai Llm guard LLM Input Output Scanning
Principles
- Principle:OWASP Www project top 10 for large language model applications Real World Incident Cross Reference
- Principle:Huggingface Diffusers Auto Docstring Generation
- Principle:Alibaba ROLL DPO Loss Computation
- Principle:Getgauge Taiko Browser Launch
- Principle:Huggingface Trl PEFT LoRA Configuration SFT
- Principle:FlagOpen FlagEmbedding Code Embedding Data Generation
- Principle:Ollama Ollama AgentArchitecture
- Principle:Pyro ppl Pyro SVI Training Loop
- Principle:Speechbrain Speechbrain HyperPyYAML Configuration
- Principle:Openai Evals YAML Registry Configuration
Implementations
- Implementation:Ggml org Ggml Ggml opt init
- Implementation:Apache Paimon KeyValue
- Implementation:Google deepmind Mujoco Engine Inline
- Implementation:FlowiseAI Flowise AgentSettingsMenu
- Implementation:Online ml River Conf RegressionJackknife
- Implementation:Interpretml Interpret CutUniform
- Implementation:Recommenders team Recommenders SARSingleNode Recommend K Items
- Implementation:Ggml org Llama cpp Common Init For Perplexity
- Implementation:Google deepmind Dm control Manipulator Base
- Implementation:Tensorflow Tfjs Tf LoadLayersModel For Transfer
Heuristics
- Heuristic:Helicone Helicone Rate Limiting Fail Open
- Heuristic:Elevenlabs Elevenlabs python Audio Buffer Sizes
- Heuristic:Mlc ai Web llm Penalty Parameter Defaults
- Heuristic:Norrrrrrr lyn WAInjectBench L2 Normalize CLIP Embeddings
- Heuristic:ClickHouse ClickHouse Debug Build Tips
- Heuristic:Vespa engine Vespa KStemmer Dictionary Loading
- Heuristic:Zai org CogVideo Scheduler and Guidance Selection
- Heuristic:Nautechsystems Nautilus trader Cache Buffer Interval Tuning
- Heuristic:BerriAI Litellm Token Counting Buffer
- Heuristic:Allenai Open instruct Warning Archived Dev Scripts
Environments
- Environment:Iamhankai Forest of Thought OpenAI API Credentials
- Environment:Microsoft Autogen Extension Optional Dependencies
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:DataTalksClub Data engineering zoomcamp Dlt BigQuery Environment
- Environment:Dotnet Machinelearning Dotnet SDK And Runtime
- Environment:BerriAI Litellm Docker Deployment
- Environment:PeterL1n BackgroundMattingV2 PyTorch CUDA
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Unstructured IO Unstructured All Docs