T5-11 B-FT

GPTKB entity

Statements (57)
Predicate Object
gptkbp:instance_of gptkb:Model
gptkbp:application natural language processing
gptkbp:architecture gptkb:T5
gptkbp:attention_heads gptkb:16
gptkbp:collaboration open-source community
gptkbp:community_support active
gptkbp:contribution transfer learning
gptkbp:developed_by gptkb:Google_Research
gptkbp:drops 0.1
gptkbp:embedding_size 1024
gptkbp:evaluates gptkb:GLUE
automatic evaluation
human evaluation
gptkbp:field_of_study gptkb:machine_learning
https://www.w3.org/2000/01/rdf-schema#label T5-11 B-FT
gptkbp:initiated_by Re LU
gptkbp:input_output gptkb:text
gptkbp:is_a_framework_for gptkb:Tensor_Flow
gptkbp:is_tasked_with text-to-text transfer
gptkbp:language English
gptkbp:layers gptkb:24
gptkbp:license gptkb:Apache_2.0
gptkbp:max_sequence_length 512
gptkbp:orbital_period 11 billion
gptkbp:performance gptkb:Super_GLUE
gptkb:SQu_AD
gptkb:MNLI
gptkb:RACE
state-of-the-art
QQP
gptkbp:predecessor gptkb:BERT
gptkbp:provides_information_on C4 dataset
gptkbp:release_date gptkb:2020
gptkbp:repository gptkb:Git_Hub
gptkbp:research_areas gptkb:AI_technology
gptkbp:research_focus language understanding
gptkbp:successor gptkb:T5-XXL
gptkbp:system_requirements TPU
gptkbp:tokenization gptkb:Sentence_Piece
gptkbp:training supervised learning
weeks
gptkbp:tuning gptkb:Adam
possible
gptkbp:type gptkb:Transformers
gptkbp:use_case gptkb:translator
question answering
text generation
text summarization
text classification
gptkbp:user_base gptkb:students
gptkb:developers
gptkb:researchers
data scientists
hobbyists
gptkbp:vocabulary_size 32000
gptkbp:bfsParent gptkb:Noam_Shazeer
gptkbp:bfsLayer 6