kssteven418/LTP
[KDD'22] Learned Token Pruning for Transformers
This project helps machine learning engineers and researchers optimize transformer models for natural language processing tasks. It takes an existing pre-trained I-BERT model, fine-tuned for tasks like text classification (e.g., sentiment analysis, question answering), and processes it to reduce its computational size and improve efficiency. The output is a smaller, faster transformer model that maintains high performance.
No commits in the last 6 months.
Use this if you are a machine learning engineer working with transformer models and need to reduce their size and improve inference speed while preserving accuracy for deployment or resource-constrained environments.
Not ideal if you are a practitioner looking for a ready-to-use, pre-optimized model without performing further training or configuration steps.
Stars
99
Forks
19
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kssteven418/LTP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
airaria/TextBrewer
A PyTorch-based knowledge distillation toolkit for natural language processing
sunyilgdx/NSP-BERT
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original...
princeton-nlp/CoFiPruning
[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
georgian-io/Transformers-Domain-Adaptation
:no_entry: [DEPRECATED] Adapt Transformer-based language models to new text domains
qiangsiwei/bert_distill
BERT distillation（基于BERT的蒸馏实验 ）