YunHaaaa/UROP
NLP, Knowledge Distillation, pruning
This project offers a collection of research papers and insights into making large language models more efficient. It distills complex AI models into smaller, faster versions, and prunes unnecessary parts, enabling them to run better on less powerful hardware. Machine learning engineers and researchers can use these insights to deploy performant NLP models.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking for methods to optimize large language models for efficiency and deployment.
Not ideal if you are looking for an out-of-the-box software tool to apply directly to your data without technical expertise.
Stars
4
Forks
—
Language
—
License
—
Category
Last pushed
May 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/YunHaaaa/UROP"
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...
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