Kvíz spojený s průvodcem · Střední úroveň
Kvíz o historii GPT
Podívejte se na milníky výzkumu GPT v letech 2018–2020, jak se kontextové příklady liší od jemného ladění a proč historické výsledky nepopisují každý produkt.
Otázka 1 z 8
What does GPT stand for in the guide?
Náhled každé otázky8 otázky
Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.
- What does GPT stand for in the guide?
- Generative Predictive Transformer
- General-Purpose Transformer
- Generative Pretrained Transformer
- Generative Prompt Tuning
- Co spojila práce GPT 2018?
- Training a task-specific supervised model from scratch using labeled examples
- Using an encoder-decoder model without unsupervised language-model pretraining
- Unsupervised language-model pretraining with supervised task adaptation
- Prompting a frozen model with examples but skipping task-specific fine-tuning
- Co zkoumal výzkum GPT-2 v roce 2019?
- Whether each task still required its own supervised parameter updates
- Whether a next-token model could attempt tasks described in text without separate task-specific training
- Whether text prompts could replace language-model pretraining entirely
- Whether every task required a separate model head and labeled dataset
- Co charakterizovalo několikanásobné hodnocení GPT-3 v roce 2020?
- A new set of weights was trained for every task prompt
- It was evaluated without examples or instructions in the prompt
- It relied on a separate fine-tuning dataset for each evaluated task
- Examples were placed in the prompt context without a task-specific gradient update for that evaluation
- Jak se liší výzva k několika snímkům od jemného doladění?
- Few-shot prompting supplies examples in context; fine-tuning updates model parameters
- Few-shot prompting updates weights, while fine-tuning keeps pretrained weights fixed
- Both methods require new gradient updates for each individual task
- Fine-tuning only retrieves documents without changing model parameters
- Co průvodce říká o jeho historické časové ose?
- It lists every current GPT product and specification
- It predicts future release dates
- It covers research milestones rather than an exhaustive current product list
- It is a live product availability page
- Why distinguish a base model from a chatbot product?
- A product is the original research model unchanged, including all of its development context
- A product may add instructions, retrieval, tools, and an interface around a model
- Adding retrieval or instructions cannot change product behavior
- Research evaluation results transfer unchanged to every product built from the model
- How should a historical benchmark result be interpreted?
- As a timeless measure of every current product
- As proof that the model solves every task
- As a guarantee of current performance
- As evidence from a particular dataset, prompt, and evaluation setting