Statements (67)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:language
|
| gptkbp:application |
natural language processing
|
| gptkbp:architecture |
gptkb:Transformers
|
| gptkbp:developed_by |
gptkb:Microsoft
|
| gptkbp:evaluates |
perplexity
BLEU score ROUGE score |
| gptkbp:feature |
API access
collaborative tools community support energy efficiency ethical considerations modularity privacy protection real-time processing safety measures scalability user-friendly interface version control robustness customization data augmentation transfer learning multi-task learning adaptability contextual understanding integration capabilities interactivity open-source contributions tutorial resources user feedback integration few-shot learning long-range dependencies interpretability model compression deployment options zero-shot learning documentation availability cloud compatibility bias mitigation local deployment semantic coherence |
| gptkbp:goal |
improve human-computer interaction
|
| gptkbp:has_ability |
text generation
language understanding |
| https://www.w3.org/2000/01/rdf-schema#label |
Turing-NLG 17 B
|
| gptkbp:language_support |
multiple languages
|
| gptkbp:orbital_period |
17 billion
|
| gptkbp:performance |
state-of-the-art
|
| gptkbp:production_company |
gptkb:Microsoft_Research
|
| gptkbp:provides_information_on |
diverse internet text
|
| gptkbp:related_to |
gptkb:GPT-3
gptkb:BERT gptkb:XLNet |
| gptkbp:release_date |
gptkb:2021
|
| gptkbp:release_type |
research model
|
| gptkbp:successor |
gptkb:Turing-NLG_3_B
|
| gptkbp:system_requirements |
high-performance GPUs
|
| gptkbp:training |
unsupervised learning
supervised fine-tuning |
| gptkbp:use_case |
gptkb:translator
question answering content creation chatbots summarization |
| gptkbp:bfsParent |
gptkb:Super_GLUE_benchmark
|
| gptkbp:bfsLayer |
5
|