https://github.com/amazon-science/meta-learning-the-difference
https://github.com/amazon-science/meta-learning-the-difference
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.4%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: amazon-science
- License: apache-2.0
- Language: Python
- Default Branch: main
- Size: 38.2 MB
Statistics
- Stars: 6
- Watchers: 2
- Forks: 0
- Open Issues: 1
- Releases: 0
Metadata Files
README.md
Meta-Learning the Difference
This is the code for the paper "Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation" by Zejiang Hou, Julian Salazar, and George Polovets, to appear in TACL 2022 (Transactions of the ACL, Vol. 10).
It is released under the Apache 2.0 license.
Library
Our dynamic low-rank task-adaptive reparameterization (TARP) and model structure (TAMS) primitives are implemented as a Python library.
sh
pip install -e .
The initial commit includes this README and the original codebases we build upon, listed below. Later commits isolate our contributions and demonstrate how the library is used, e.g., TARP and TAMS in a meta-learning the difference loop on top of a HuggingFace Transformers model.
dialogue_personalization/ reproduces our work on Persona-Chat. It is based on https://github.com/HLTCHKUST/PAML (MIT license) which was released with the paper "Personalizing Dialogue Agents via Meta-Learning" by Zhaojiang Lin, Andrea Madotto, Chien-Sheng Wu, Pascale Fung at ACL 2019.
abstractive_summarization/ reproduces our work on AdaptSum. It is based on https://github.com/TysonYu/AdaptSum (CC BY 4.0 license) which was released with the paper "AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization" by Tiezheng Yu, Zihan Liu, Pascale Fung at NAACL-HLT 2021.
low_rank_comparisons/ reproduces comparisons with other efficient adaptation papers. It is based on https://github.com/microsoft/LoRA/tree/snapshot-9-15-2021 (MIT license) which was released with the preprint "LoRA: Low-Rank Adaptation of Large Language Models" by Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Weizhu Chen.
Owner
- Name: Amazon Science
- Login: amazon-science
- Kind: organization
- Website: https://amazon.science
- Twitter: AmazonScience
- Repositories: 80
- Profile: https://github.com/amazon-science
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Issues and Pull Requests
Last synced: over 1 year ago
All Time
- Total issues: 0
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 1
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- nltk *
- numpy *
- tqdm *
- transformers ==4.12.5
- pytorch-pretrained-bert ==0.6.2
- tensorboardX ==1.6
- torch ==0.4.1
- tqdm ==4.32.1
- progress *
- spacy *
- tensorboard *
- torch ==1.7.1
- tqdm *
- transformers ==3.3.1
- torch *