Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction
Overview of ParlAI Features and Architecture
- ParlAI framework
- Key capabilities and objectives
- Core concepts (agents, messages, teachers, and worlds)
Getting Started with ParlAI for Conversational AI
- Installation process
- Incorporating a simple model
- Simple display data script
- Validation and testing procedures
- Tasks
- Agent training and evaluation
- Interacting with models
Working with Tasks and Datasets in ParlAI
- Adding datasets
- Segregating data into sets (train, valid, or test)
- Utilizing JSON instead of text files
- Creating and executing tasks
Exploring Worlds, Sharing, and Batching
- The concept of Worlds
- Agent sharing
- Implementing batching
- Dynamic batching
Using Torch Generator and Ranker Agents
- Torch generator agent
- Torch ranker agent
- Example models
- Creating models
- Training and evaluating models
Adding Built-In and Custom Metrics
- Standard metrics
- Adding custom metrics
- Teacher metrics
- Agent-level metrics (global and local)
- List of metrics
Accelerating Training Runs in ParlAI
- Establishing a baseline
- Skip generation command
- Dynamic batching training command
- Utilizing FP16 and multiple GPUs
- Background preprocessing
Exploring Other ParlAI Topics
- Using and writing mutators
- Running crowdsourcing tasks
- Leveraging existing chat services
- Substituting transformer subcomponents
- Running and writing tests
- ParlAI tips and tricks
Troubleshooting
Summary and Conclusion
Requirements
- Proficiency in Python or other programming languages.
- A general understanding of artificial intelligence (AI) concepts.
Target Audience
- Researchers
- Developers
14 Hours
