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
Foundations of Open-Source LLMs
- Surveying DeepSeek, Mistral, LLaMA, and other open-source frameworks.
- Exploring LLM mechanics: Transformers, self-attention mechanisms, and training processes.
- Benchmarking open-source LLMs against proprietary solutions.
Refining and Adapting LLMs
- Preparing data sets for fine-tuning initiatives.
- Training and optimizing models via Hugging Face.
- Assessing model performance and strategies for bias reduction.
Constructing AI Agents with LLMs
- Utilizing LangChain for AI agent architecture.
- Architecting agent-centric workflows integrated with LLMs.
- Implementing memory, retrieval-augmented generation (RAG), and action execution.
Rolling Out LLM-Driven AI Agents
- Encapsulating AI agents using Docker.
- Embedding LLMs into enterprise software ecosystems.
- Scaling AI agents through cloud infrastructure and APIs.
Security and Compliance in Corporate AI
- Navigating ethical standards and regulatory obligations.
- Mitigating risks associated with AI-driven automation.
- Monitoring and auditing the behavior of AI agents.
Practical Examples and Industry Applications
- LLM-enabled virtual assistants.
- AI-enhanced document processing.
- Bespoke AI agents for corporate analytics.
Enhancing and Sustaining LLM-Based Agents
- Implementing continuous model refinement and updates.
- Establishing monitoring systems and feedback mechanisms.
- Strategies for cost efficiency and performance optimization.
Recap and Future Directions
Requirements
- Solid proficiency in AI and machine learning concepts.
- Practical experience in Python development.
- Working knowledge of large language models (LLMs) and natural language processing (NLP).
Target Audience
- AI engineers.
- Enterprise software developers.
- Business leaders.
21 Hours
