arazd/ProgressivePrompts
Progressive Prompts: Continual Learning for Language Models
This project helps machine learning engineers and researchers improve how large language models (LLMs) learn new tasks over time without forgetting what they've already learned. It takes an existing T5 or BERT-based language model and a stream of new tasks or datasets, then produces an enhanced model that can handle current tasks while retaining proficiency in previous ones. This is designed for those building and deploying LLMs in environments where models need to adapt continuously to new information.
No commits in the last 6 months.
Use this if you are developing large language models that need to continually learn new information or tasks without 'forgetting' previously acquired knowledge, addressing a common challenge in AI development.
Not ideal if you are looking for an off-the-shelf, end-user application for language models, as this is a technical tool for model development and training.
Stars
98
Forks
14
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/arazd/ProgressivePrompts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
debjitpaul/refiner
About The corresponding code from our paper " REFINER: Reasoning Feedback on Intermediate...
THUDM/P-tuning
A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
ZixuanKe/PyContinual
PyContinual (An Easy and Extendible Framework for Continual Learning)
Nithin-Holla/MetaLifelongLanguage
Repository containing code for the paper "Meta-Learning with Sparse Experience Replay for...
SALT-NLP/IDBR
Codes for the paper: "Continual Learning for Text Classification with Information...