Training एक ML model को data से सिखाने की प्रक्रिया है (patterns सीखना, parameters adjust करना), जबकि inference trained model का उपयोग करके new data पर predictions बनाना है। ये अलग-अलग characteristics और costs वाले विशिष्ट phases हैं।
Training vs inference
text
TRAINING → teaching the model (the LEARNING phase):
→ feed lots of DATA → the model adjusts its parameters to learn patterns
→ computationally EXPENSIVE (lots of data, compute, time — e.g. training an LLM costs
huge resources); done once (or periodically to update)
→ produces a trained MODEL
INFERENCE → using the trained model (the PREDICTION phase):
→ give the trained model NEW input → it produces an output (prediction/generation)
→ much CHEAPER/faster than training (a single forward pass); done MANY times (every
time you use the model)
→ train once (expensive), infer many times (cheaper, in production)