Quantization and Model Compression — Fine-Tuning & Model Customizatio…
Shrinking models without losing too much quality
Steps in Quantization and Model Compression
- Quantization Fundamentals — beginner · Reducing model precision to save memory and increase speed
- Post-Training Quantization — beginner · Quantizing a model after training without retraining it
- Quantization-Aware Training — beginner · Training with quantization in mind for better final quality
- Model Distillation — beginner · Training a smaller model to mimic a larger one
- Trade-offs Between Compression Techniques — beginner · Comparing quantization, distillation and pruning
Part of
- Fine-Tuning & Model Customization roadmap — the full learning path