Fine-Tuning vs RAG vs Kedis degdeg ah

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Qaabka ayaa si khaldan uga jawaabaya su'aalaha ku saabsan qiimaha shirkaddaada sababtoo ah qiimuhu wuu isbedelaa rubuci kasta. Habkee ugu habboon farqigan?
   • Fine-tune the model on last quarter's price list
   • Use RAG to retrieve the current price documents at answer time
   • Lower the model's temperature
   • Add more examples of polite answers to the prompt
2. Marka loo eego hagaha, waa maxay inta badan kabaalka ugu horreeya ee isku daya dhibaatooyinka qaabka iyo qaabka?
   • Full fine-tuning
   • Building a vector database
   • Prompting with clear instructions and examples
   • Switching to a larger model
3. Maxaa hagaajinta hagaajinta loogu tilmaamay hab aan la isku halayn karin oo lagu kordhinayo aqoonta dhabta ah?
   • It cannot change model weights
   • Waxay kaliya ku shaqeysaa moodooyinka sawirka
   • It is hard to update and can increase confident errors about rarely seen material
   • It always deletes the model's existing knowledge
4. Xaaladdee ayaa sida cad u jecel hagaajinta?
   • You need a narrow task done at high volume and want a smaller, cheaper model to match a larger one
   • Your documents change every day
   • You want answers to cite source passages
   • You have not yet built any evaluation examples
5. Nidaamka RAG oo siinaya jawaabo khaldan, maxaad tahay inaad hubiso ka hor intaadan eedayn qaabka luqadda?
   • Taariikhda tababarka modelka
   • Whether the correct passage appears in the retrieved results
   • The number of GPU cores
   • The length of the system prompt only
6. What does LoRA do in the context of fine-tuning?
   • Retrieves documents from a search index
   • Compresses prompts to save tokens
   • Trains small adapter matrices instead of updating all model weights
   • Removes the need for training data
7. Which statement about combining the three methods is accurate according to the guide?
   • They are mutually exclusive and cannot be combined
   • Production systems often use a fine-tuned model reading retrieved context, driven by a good prompt
   • RAG replaces the need for any prompt
   • Fine-tuning must always come before prompting
8. What should drive the choice between prompting, RAG and fine-tuning?
   • Whichever method is newest
   • A representative evaluation set measuring each option
   • The vendor's default setting
   • The size of the training budget alone