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.
Duration 7 hours
Course Outline
Transitioning from Text Generation to Typed Decisions
- Understanding the output structure of decision models.
- Distinguishing System One decisions from reasoning LLM processes.
- Examining the cost and latency characteristics of bounded decisions.
The Landscape of Open-Weight Decision Models
- Strands Decider 2B by AWS Labs.
- The JEV and GEV open-weight model families.
- Pplx-Decider, Liquid D1, and Clef.
- Differences in licensing and deployment strategies.
Anatomy of a Decision Model
- Utilizing an LLM torso without a language modelling head.
- Scoring candidate options via the pointer head mechanism.
- Deriving confidence scores from the model’s output.
Implementing Your First Decisions
- Setting up local environments on CPU and consumer-grade GPUs.
- Structuring effective questions and defining option sets.
- Processing multiple queries in a single inference pass.
- Managing thresholds and defining fallback behaviors.
Evaluating Decision Quality
- Utilizing JevBench and other decision-specific benchmarks.
- Balancing accuracy with calibration performance.
- Assessing confidence reliability using the Brier score.
- Identifying scenarios where a decision model is not the appropriate tool.
Requirements
- A foundational understanding of large language models and prompt-driven applications.
- Proficiency with command-line interfaces and Python scripting.
- No prior experience in machine learning training is necessary.
Target Audience
- AI engineers assessing decision models for integration into agent workflows.
- Software developers looking to replace open-ended LLM calls with bounded decision logic.
- Solution and platform architects developing agent-based architectures.
- Technical product managers evaluating options for decision models.
