Distillation and model compression · MLD-0471
GPTQ
A post-training weight-quantization method using approximate second-order information to reduce reconstruction error.
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 low-bit language-model weights.
Original caveat
Method name does not limit it to one branded GPT model.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: DL · SLM · LLM.
Aliases: None recorded.
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 ↗