Distillation and model compression · MLD-0975
Quantization-aware training
Training while simulating or accounting for quantization effects.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Prepare a model for low-precision deployment.
Original caveat
Training operations often still use higher precision internally.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: DL · SLM · LLM.
Aliases: QAT.
Related concepts
Concepts linking here
Original references
- Distilling the Knowledge in a Neural Network ↗ · Consulted
- PEFT: LoRA conceptual guide ↗ · Consulted
- PEFT: quantization guide ↗ · Consulted
- Original reference URL ↗