airaria/TextBrewer
A PyTorch-based knowledge distillation toolkit for natural language processing
This toolkit helps machine learning engineers and NLP researchers make large language models run faster and use less memory without significantly losing accuracy. You provide a powerful, high-performing 'teacher' model and a smaller 'student' model, and it helps the student learn from the teacher to achieve near-teacher performance. The output is a compact, optimized language model ready for deployment in real-world applications.
1,697 stars. No commits in the last 6 months.
Use this if you need to deploy large language models for tasks like text classification, question answering, or named entity recognition in environments with limited computational resources or strict latency requirements.
Not ideal if you are working with non-text data or if you need to build a language model from scratch without a larger 'teacher' model to learn from.
Stars
1,697
Forks
246
Language
Python
License
Apache-2.0
Category
Last pushed
May 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/airaria/TextBrewer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
sunyilgdx/NSP-BERT
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original...
kssteven418/LTP
[KDD'22] Learned Token Pruning for Transformers
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 ）