> ## Documentation Index > Fetch the complete documentation index at: https://docs.flex.ai/llms.txt > Use this file to discover all available pages before exploring further. # Blueprints > A set of end-to-end experiments to explore FlexAI — from your first training job to advanced fine-tuning, inference, and multi-agent applications. This section provides **a set of different experiments** designed for you to try out and explore **FlexAI**. These experiments range from running your very first training job, to fine-tuning language, diffusion, and text-to-speech models using techniques like QLoRA and LoRA, as well as integrating FlexAI with other platforms, such as experiment trackers. ## Getting Started ### Prerequisites **FlexAI CLI**: Install the FlexAI CLI by following the steps shown in the [Installing the FlexAI CLI](/cli/install) guide. ## The Experiments The following table lists out the experiments available. Each experiment is designed to walk you through a specific use case and contains its required code, as well as detailed instructions on how to run it on FlexAI: | No. | Section | Description | | --- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | | 1 | [A Simple Training Job on FlexAI](/blueprints/running-a-simple-training-job) | Step-by-step guide to get your first Training Job on FlexAI running | | 2 | [A Simple Distributed Data Parallel (DDP) Training Job on FlexAI](/blueprints/running-a-simple-training-job-with-ddp) | Demonstrates that you only need to add 2 flags in order to start a DDP Training Job | | 3 | [Resuming a Training Job from a Checkpoint](/blueprints/continuing-a-training-job-from-a-checkpoint) | Learn how to resume a Training Job from a previously saved checkpoint | | 4 | [Streaming Large Datasets During a Training Job](/blueprints/streaming-datasets) | Train a model on a large dataset using streaming | | 5 | [Training Job & Experiment Tracking](/blueprints/integrating-a-experiment-tracker) | Using Weights and Biases with FlexAI for *experiment tracking* | | 6 | [Fine-Tuning a Language Model with QLoRA](/blueprints/qlora-ft-on-a-language-model) | Fine-tune a causal language model efficiently using QLoRA | | 7 | [Fine-Tuning a Diffusion Model with LoRA](/blueprints/lora-ft-on-a-diffusion-model) | Fine-tune a diffusion model efficiently using LoRA | | 8 | [Fine-Tuning a Text-to-Speech Model](/blueprints/ft-on-a-tts-model) | Fine-tune a text-to-speech (TTS) model | | 9 | [Fine-Tuning a Language Model using Flash Attention](/blueprints/flash-attention-ft-on-a-language-model) | Fine-tune a causal language model efficiently using the flash-attn package | | 10 | [Train and Serve a French LLM on FlexAI with LlamaFactory](/blueprints/llama-factory) | Fine-tune Qwen2.5-7B on French data using LlamaFactory and deploy as a production-ready inference endpoint | | 11 | [Train and Serve Language Models with Axolotl](/blueprints/axolotl) | Fine-tune language models on domain-specific data using Axolotl framework with custom dataset configurations and FSDP | | 12 | [Reinforcement Learning Fine-Tuning with EasyR1](/blueprints/easyR1) | Train language models with RL using GRPO and DAPO algorithms for enhanced reasoning capabilities | | 13 | [GRPO Training on Vision-Language Models](/blueprints/vlm-grpo) | Fine-tune vision-language models using GRPO reinforcement learning with HuggingFace TRL, LoRA, vLLM, and DeepSpeed ZeRO-3 | | 14 | [Language Model Evaluation with LM-Evaluation-Harness](/blueprints/lm-evaluation-harness) | Comprehensive evaluation of language models across 300+ tasks and benchmarks | | 15 | [RAG Application with LangChain and FlexAI Inference Endpoints](/blueprints/rag-application) | Interactive interface for users to ask questions based on provided documents using Retrieval-Augmented Generation | | 16 | [Speech-to-Text Application Using FlexAI Inference Endpoints](/blueprints/speech-to-text-inference) | Interactive interface for recording audio messages and receiving transcriptions | | 17 | [Multi-Agent Orchestration with LangGraph](/blueprints/multi-agent) | Build a multi-agent system where specialized AI agents work together under a central supervisor | | 18 | [Text-to-Image Inference with FlexAI Endpoints](/blueprints/text-to-image-inference) | Deploy and use Stable Diffusion 3.5 Large for high-quality image generation via FlexAI inference endpoints | | 19 | [Text-to-Audio Inference with FlexAI Endpoints](/blueprints/text-to-audio-inference) | Deploy and use Stable Audio Open 1.0 for high-quality audio generation via FlexAI inference endpoints | | 20 | [Text-to-Speech Inference with FlexAI Endpoints](/blueprints/text-to-speech-inference) | Deploy and use the Kokoro model for natural voice synthesis via FlexAI inference endpoints | | 21 | [Text-to-Video Inference with FlexAI Endpoints](/blueprints/text-to-video-inference) | Deploy and use Wan2.2-T2V-A14B for high-quality video generation via FlexAI inference endpoints | | 22 | [Object Detection and Computer Vision with Ultralytics YOLO11](/blueprints/ultralytics) | Train and deploy state-of-the-art object detection, segmentation, and pose estimation models using YOLO11 | | 23 | [Text-to-Speech Inference with Qwen3-TTS and FlexAI Endpoints](/blueprints/text-to-audio-qwen3-tts) | Interactive Qwen3-TTS interface for high-quality text-to-speech synthesis | *** ## Keep in mind ### Notes on HuggingFace Accelerate Integration This section includes experiments that utilize the **HuggingFace Accelerate library** for efficient training. The **FlexAI CLI** simplifies running training scripts by automatically determining the appropriate execution method: * **`python`**: Used for single-accelerator training. * **`torchrun`**: Automatically used for multi-accelerator distributed training. If you're accustomed to using the **`accelerate launch`** command, you can seamlessly run the same scripts on FlexAI without modification. Simply provide the script to FlexAI, and it will handle execution. As highlighted in the [Accelerate documentation](https://huggingface.co/docs/accelerate/en/basic_tutorials/launch#using-accelerate-launch), the `accelerate launch` command is optional. Instead, the Accelerate functionality integrates directly into your script, making it compatible with other launchers like `torchrun`. Unlike `accelerate launch`, `torchrun` does not use the YAML configuration file generated by `accelerate config`. If your training setup relies on specific configurations from the YAML file, you may need to adjust your script to explicitly define these settings using the `Accelerator` class. By doing so, you ensure seamless execution across different environments while maintaining flexibility for various training setups.