|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:applies_to
|
Question answering
|
|
gptkbp:architectural_style
|
gptkb:Transformers_character
|
|
gptkbp:based_on
|
BERT architecture
|
|
gptkbp:collaborated_with
|
Academic institutions
|
|
gptkbp:competes_with
|
gptkb:Distil_BERT
|
|
gptkbp:developed_by
|
gptkb:Huawei
Collaborative efforts
Chinese language tasks
|
|
gptkbp:has_achievements
|
SOTA performance
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Tiny BERT-4
|
|
gptkbp:improves
|
Inference speed
|
|
gptkbp:is_adopted_by
|
Tech companies
Industry applications
|
|
gptkbp:is_analyzed_in
|
Model robustness
|
|
gptkbp:is_available_on
|
gptkb:Hugging_Face_Model_Hub
|
|
gptkbp:is_compared_to
|
ALBERT
|
|
gptkbp:is_compatible_with
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_considered_as
|
Lightweight model
|
|
gptkbp:is_designed_for
|
Resource-constrained environments
|
|
gptkbp:is_documented_in
|
Research papers
|
|
gptkbp:is_evaluated_by
|
gptkb:GLUE_benchmark
Speed and accuracy
User experience
Cross-validation
Model interpretability
|
|
gptkbp:is_explored_in
|
AI research conferences
|
|
gptkbp:is_influenced_by
|
gptkb:BERT
|
|
gptkbp:is_integrated_with
|
AI platforms
|
|
gptkbp:is_optimized_for
|
Mobile devices
|
|
gptkbp:is_part_of
|
NLP toolkits
Tiny BERT family
AI model ecosystem
|
|
gptkbp:is_promoted_by
|
gptkb:Huawei_Technologies
|
|
gptkbp:is_recognized_for
|
Efficiency
|
|
gptkbp:is_related_to
|
gptkb:software
|
|
gptkbp:is_supported_by
|
Open-source community
Community contributions
|
|
gptkbp:is_tested_for
|
Scalability
Benchmark datasets
Real-world data
Baseline models
Sentiment datasets
|
|
gptkbp:is_used_by
|
gptkb:physicist
|
|
gptkbp:is_used_for
|
Sentiment analysis
Feature extraction
|
|
gptkbp:is_used_in
|
Chatbots
|
|
gptkbp:is_utilized_in
|
Text summarization
Virtual assistants
Text generation
Dialogue systems
|
|
gptkbp:orbital_period
|
14 million
|
|
gptkbp:performance
|
gptkb:BERT
F1 score
|
|
gptkbp:purpose
|
gptkb:software
|
|
gptkbp:release_date
|
gptkb:2021
|
|
gptkbp:research
|
Model compression
|
|
gptkbp:size
|
4 layers
|
|
gptkbp:supports
|
Multi-task learning
|
|
gptkbp:training
|
Masked language modeling
Chinese corpus
|
|
gptkbp:tuning
|
Text classification
|
|
gptkbp:uses
|
Knowledge Distillation
|
|
gptkbp:bfsParent
|
gptkb:Tiny_BERT
|
|
gptkbp:bfsLayer
|
5
|