quiz bu lëkkale ak tegtal · Dëgër Niveau
Optimisation otomatik ak quiz DSPy
Saytu li nga xam ci laaj poñ yi ci benn metric, ni APE ak OPRO di seetee ay tegtal, ak ni siif DSPy ak optimisateurs di doxee.
Laaj 1 de 8
Lan ngay wara joxe ngir optimisation automatique bi mëna dox?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- Lan ngay wara joxe ngir optimisation automatique bi mëna dox?
- Only a longer prompt
- A task, a set of example inputs and a metric to score outputs
- A fine-tuned model and a GPU cluster
- A list of banned words
- Ci OPRO, lan mooy liggéeyu optimisatër bi?
- A gradient descent step on the model's weights
- A human prompt engineer
- A random search with no feedback
- An LLM given a meta-prompt listing earlier instructions and their scores
- Lan la OPRO's "Noyyil bu baax nga liggéey ci jafe-jafe bii jéego par jéego" di wane?
- Optimized wording can be unintuitive and specific to a model
- Breathing instructions work for every model
- Math tasks do not need prompts
- OPRO only works for writing tasks
- Luy siife DSPy?
- A cryptographic key for the API
- A model's version number
- A declaration of a step's inputs and outputs, such as "question, context -> answer"
- A watermark on generated text
- naka la BootstrapFewShot bu DSPy di amee ay firndeem?
- It downloads examples from the internet
- It runs the program on training inputs and keeps the traces where the metric passes
- It asks the user to label every intermediate step
- It uses the longest available examples
- Why should you keep a separate held-out set when optimizing prompts?
- To reduce the size of the prompt
- To make the optimizer run faster
- It is required by the API
- To check whether the optimized prompt has overfit the training examples
- What were DSPy's optimizers called earlier?
- Teleprompters
- Compilers
- Tokenizers
- Retrievers
- What approach did APE (Automatic Prompt Engineer) take?
- It fine-tuned model weights on instructions
- It hand-wrote prompts from expert interviews
- It had a model propose instructions from input-output examples and kept the highest-scoring ones
- It removed instructions entirely