Ikibazo gihuza ibibazo · Biragoye Urwego
Automatic Byihuse Optimisation hamwe na DSPy Ikibazo
Gerageza ibyo uzi kubijyanye no gutanga amanota kubipimo, uko APE na OPRO bashakisha amabwiriza, nuburyo imikono ya DSPy na optimizers ikora.
Ikibazo 1 Bya 8
Niki ugomba gutanga kugirango uhite ukora neza kugirango ukore?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Niki ugomba gutanga kugirango uhite ukora neza kugirango ukore?
- 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
- Muri OPRO, niki kigira uruhare rwa optimizer?
- 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
- "OPRO uhumeka neza kandi ukore kuri iki kibazo intambwe ku yindi" byerekana iki?
- 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
- Umukono wa DSPy ni iki?
- 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
- Nigute BootstrapFewShot ya DSPy ibona imyiyerekano yayo?
- 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