Swift DOCUMENTATION

Get Started

• SWIFT Installation
  • Wheel Packages Installation
  • Source Code Installation
  • Older Versions
  • Mirror
  • Supported Hardware
  • Running Environment
  • Notebook Environment
• Quick Start
  • Installation
  • Usage Example
  • Learn More
• Web-UI

Instruction

• Command Line Parameters
  • Base Arguments
  • Atomic Arguments
  • Integration Arguments
  • Specific Model Arguments
  • Other Environment Variables
• Pre-training and Fine-tuning
  • Environment Preparation
  • Pre-training
  • Fine-tuning
  • Merge LoRA
  • Inference (Fine-Tuned Model)
  • Deployment (Fine-Tuned Model)
• GRPO
  • Get Started
  • Developer Guide
  • Advanced Research
• RLHF
  • Dataset
  • GRPO
  • DPO
  • RM
  • PPO
  • KTO
  • CPO
  • ORPO
  • SimPO
• Inference and Deployment
  • Inference
  • Deployment
• Megatron-SWIFT Training
  • Environment Setup
  • Quick Start Example
  • Benchmark
  • Command Line Arguments
• Sampling
  • Capability Introduction
  • Environment Setup
  • Using PRM and ORM for Result Filtering
  • Customizing PRM or ORM
  • Memory Control
  • Practical Example
  • Sampling From Large Model
• Evaluation
  • Capability Introduction
  • Environment Preparation
  • Evaluation
  • Evaluation During Training
  • Custom Evaluation Datasets
  • Question-and-Answer Format (QA)
• Export and Push
  • Merge LoRA
  • Quantization
  • Push Model
• Reinforced Fine-Tuning
  • Concept of Reinforced Fine-Tuning
  • When to Use Reinforced Fine-Tuning
  • SWIFT Implementation
  • Experimental Results
  • Future Roadmap
• Agent Support
  • Dataset Format
  • Tools Format
  • Usage of loss_scale
  • Training
  • Inference
  • Deployment
• Supported Models and Datasets
  • Large Language Models
  • Datasets
• Using Tuners
  • Interface List
• Frequently-asked-questions
  • Training
  • Inference
  • Deployment
  • Evaluation

Customization

• Custom Model
  • Model Registration
• Custom Dataset
  • Standard Dataset Format
  • dataset_info.json
  • Dataset Registration
• Pluginization
  • Callback Mechanism
  • Customizing Loss
  • Customizing Loss Scale
  • Customizing Metrics
  • Customizing Optimizers
  • Customizing Agent Template
  • Customizing Tuners
  • PRM (Process Reward Model)
  • ORM (Outcome Reward Model)

Best Practices

• Complete GRPO Experiment Process
  • Task and Dataset Definition
  • Reward Function Definition
  • GRPO Training Experiment Record
• Complete Multimodal GRPO Experiment Workflow
  • ClevrCount Task
  • Reward Function Definition
  • Geometric QA Task
  • Multimodal Open R1 Dataset Experiment
• Code Training with GRPO
  • Reward Functions
  • Training Script
• Qwen3 Best Practices
  • Inference
  • Training
  • Supervised Fine-Tuning (SFT)
  • Reinforcement Learning (RL)
  • Megatron-SWIFT
• Embedding Training
  • Loss
  • Dataset Format
  • Scaffolding
  • Inference
• Reranker Training
  • Implementation Methods
  • Loss Function Types
  • Dataset Format
  • Training Scripts
• Best Practices for Rapidly Training Vision-Language (VL) Models
  • Model Modification
  • Training
  • Inference / Deployment / Evaluation
• NPU Support
  • Environment Preparation
  • Fine-tuning
  • Inference
  • Deployment
• More Best Practices

Indices and tables

• Index

• Module Index

• Search Page