# AITraining

## Docs

- [Distributed Training](https://docs.monostate.ai/advanced/distributed-training.md): Multi-GPU and multi-node training with DDP and DeepSpeed
- [DPO Training](https://docs.monostate.ai/advanced/dpo-training.md): Direct Preference Optimization for alignment
- [Flash Attention](https://docs.monostate.ai/advanced/flash-attention.md): Speed up training with Flash Attention 2
- [GRPO Training](https://docs.monostate.ai/advanced/grpo-training.md): Group Relative Policy Optimization with Custom Environments
- [Hyperparameter Sweeps](https://docs.monostate.ai/advanced/hyperparameter-sweeps.md): Automatically find optimal training settings
- [LoRA & PEFT](https://docs.monostate.ai/advanced/lora-peft.md): Efficient fine-tuning with adapters
- [ORPO Training](https://docs.monostate.ai/advanced/orpo-training.md): Odds Ratio Preference Optimization
- [PPO Training](https://docs.monostate.ai/advanced/ppo-rl-training.md): Reinforcement Learning from Human Feedback with PPO
- [Prompt Distillation](https://docs.monostate.ai/advanced/prompt-distillation.md): Train smaller models to mimic larger ones
- [Quantization](https://docs.monostate.ai/advanced/quantization.md): Reduce memory with quantized training
- [Reward Modeling](https://docs.monostate.ai/advanced/reward-modeling.md): Train reward models for RLHF
- [RL Training Module](https://docs.monostate.ai/advanced/rl-module.md): Advanced reinforcement learning for LLMs
- [Unsloth Integration](https://docs.monostate.ai/advanced/unsloth-integration.md): Faster LoRA training with Unsloth
- [Authentication](https://docs.monostate.ai/api/authentication.md): Configure API tokens and authentication
- [Error Handling](https://docs.monostate.ai/api/error-handling.md): Handle errors and exceptions in your code
- [API Introduction](https://docs.monostate.ai/api/introduction.md): Use AITraining programmatically with Python
- [LLM Endpoints](https://docs.monostate.ai/api/llm-endpoints.md): API for training large language models
- [Python SDK](https://docs.monostate.ai/api/python-sdk.md): Complete Python API reference
- [Rate Limits](https://docs.monostate.ai/api/rate-limits.md): Understanding rate limits and quotas
- [Changelog](https://docs.monostate.ai/changelog.md): Release notes and bug fixes for AITraining
- [Conversation](https://docs.monostate.ai/chat/conversation.md): Chat with your trained models
- [Interface Overview](https://docs.monostate.ai/chat/interface-overview.md): Understanding the chat interface layout
- [Launching Chat](https://docs.monostate.ai/chat/launching.md): Start the chat interface to test your models
- [Loading Models](https://docs.monostate.ai/chat/loading-models.md): Load trained models into the chat interface
- [Generation Parameters](https://docs.monostate.ai/chat/parameters.md): Control how your model generates responses
- [Batch Processing](https://docs.monostate.ai/cli/batch-processing.md): Run multiple training jobs efficiently
- [Benchmarking](https://docs.monostate.ai/cli/benchmarking.md): Measure and compare model performance
- [Command Structure](https://docs.monostate.ai/cli/command-structure.md): Understanding the AITraining CLI syntax
- [Config Templates](https://docs.monostate.ai/cli/config-templates.md): Ready-to-use configuration templates
- [Custom Scripts](https://docs.monostate.ai/cli/custom-scripts.md): Extend AITraining with custom scripts
- [Environment Variables](https://docs.monostate.ai/cli/environment-variables.md): Configure AITraining via environment variables
- [Global Options](https://docs.monostate.ai/cli/global-options.md): Options available across all CLI commands
- [Help System](https://docs.monostate.ai/cli/help-system.md): Navigate the CLI help and documentation
- [Inference Mode](https://docs.monostate.ai/cli/inference-mode.md): Run inference with trained models
- [Installation & Setup](https://docs.monostate.ai/cli/installation-setup.md): Get AITraining CLI ready to use
- [LLM Training](https://docs.monostate.ai/cli/llm-training.md): Train large language models with the CLI
- [Logging & Debugging](https://docs.monostate.ai/cli/logging-debugging.md): Monitor training and debug issues
- [Model Serving](https://docs.monostate.ai/cli/model-serving.md): Serve trained models as APIs
- [Pipeline Automation](https://docs.monostate.ai/cli/pipeline-automation.md): Automate training workflows
- [Tabular Data](https://docs.monostate.ai/cli/tabular-data.md): Train models on structured tabular data
- [Text Tasks](https://docs.monostate.ai/cli/text-tasks.md): Train text classification, regression, and NER models
- [Vision Tasks](https://docs.monostate.ai/cli/vision-tasks.md): Train image classification, detection, and VLM models
- [YAML Configs](https://docs.monostate.ai/cli/yaml-configs.md): Use configuration files for training
- [When to Use the API](https://docs.monostate.ai/foundations/api-when-to-use.md): Python integration for custom applications
- [When to Use the Chat Interface](https://docs.monostate.ai/foundations/chat-when-to-use.md): Visual interface for testing and interacting with trained models
- [Choosing Your Interface](https://docs.monostate.ai/foundations/choosing-interface.md): CLI, Chat, or API - pick the right tool
- [Choosing Your Approach](https://docs.monostate.ai/foundations/choosing-your-approach.md): Decide between fine-tuning, training from scratch, or prompt engineering
- [When to Use the CLI](https://docs.monostate.ai/foundations/cli-when-to-use.md): Command line for automation and scripting
- [Datasets and Formats](https://docs.monostate.ai/foundations/datasets-and-formats.md): How to structure your training data
- [Entropy & Uncertainty](https://docs.monostate.ai/foundations/entropy-uncertainty.md): Understanding the mathematical roots of model behavior
- [Evaluation Metrics](https://docs.monostate.ai/foundations/evaluation-metrics.md): How to measure if your model is good
- [Fine-tuning vs Full Training](https://docs.monostate.ai/foundations/fine-tuning-vs-full-training.md): Start from scratch or build on existing models
- [Hallucinations & Limitations](https://docs.monostate.ai/foundations/hallucinations-limitations.md): Understanding when AI models get things wrong
- [How Training Works](https://docs.monostate.ai/foundations/how-training-works.md): The technical process behind AI training
- [Hyperparameters](https://docs.monostate.ai/foundations/hyperparameters.md): The knobs and dials of training
- [Installation](https://docs.monostate.ai/foundations/installation.md): Set up AI Training on your system
- [Welcome to AI Training](https://docs.monostate.ai/foundations/introduction.md): Train custom AI models without the complexity
- [Model Types](https://docs.monostate.ai/foundations/model-types.md): Different architectures for different tasks
- [Quick Start](https://docs.monostate.ai/foundations/quickstart.md): Train your first AI model in 10 minutes
- [Small Models Can Win](https://docs.monostate.ai/foundations/small-models-win.md): How measurement science inspired a breakthrough
- [Training Tasks](https://docs.monostate.ai/foundations/training-tasks.md): What you can train models to do
- [Transformers Explained](https://docs.monostate.ai/foundations/transformers-explained.md): Understanding the architecture behind modern AI
- [Understanding AI Training](https://docs.monostate.ai/foundations/understanding-ai-training.md): How AI models learn from data
- [What is AI Training](https://docs.monostate.ai/foundations/what-is-aitraining.md): Learn what this platform does and how it helps you
- [Roadmap](https://docs.monostate.ai/roadmap.md): Upcoming features and training tasks
- [Choosing Models](https://docs.monostate.ai/wizard/choosing-models.md): How to select the right model for your hardware and use case
- [Wizard Commands](https://docs.monostate.ai/wizard/commands.md): All commands and shortcuts available in the wizard
- [Dataset Guide](https://docs.monostate.ai/wizard/dataset-guide.md): Understanding datasets, formats, and what works best for your model
- [Interactive Wizard](https://docs.monostate.ai/wizard/overview.md): Train your first model with zero configuration
- [SFT Training Walkthrough](https://docs.monostate.ai/wizard/sft-walkthrough.md): Complete step-by-step guide to train your first LLM

## Optional

- [GitHub](https://github.com/monostate/aitraining)
- [PyPI](https://pypi.org/project/aitraining)
- [Discord](https://discord.gg/monostate)