cambridgeltl / composable-sftView external linksLinks
A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.
☆75Aug 9, 2024Updated last year
Alternatives and similar repositories for composable-sft
Users that are interested in composable-sft are comparing it to the libraries listed below
Sorting:
- Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).☆59Jan 14, 2022Updated 4 years ago
- ☆13Dec 11, 2021Updated 4 years ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆74Mar 2, 2024Updated last year
- Language-agnostic BERT Sentence Embedding (LaBSE) Pytorch Model☆21Sep 2, 2020Updated 5 years ago
- ☆46Apr 13, 2022Updated 3 years ago
- Code for paper "UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning", ACL 2022☆63Mar 23, 2022Updated 3 years ago
- Minute-long video generation at 24FPS.☆50Feb 2, 2026Updated last week
- Source code repo for paper "TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation"☆10Aug 11, 2023Updated 2 years ago
- This repositary hosts my experiments for the project, I did with OffNote Labs.☆10Apr 12, 2021Updated 4 years ago
- ☆25Jul 12, 2022Updated 3 years ago
- Collect papers about Mamba (a selective state space model).☆14Aug 6, 2024Updated last year
- Code for "Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model", EMNLP Findings 20…☆28Nov 2, 2023Updated 2 years ago
- Reproducing RigL (ICML 2020) as a part of ML Reproducibility Challenge 2020☆29Jan 6, 2022Updated 4 years ago
- Adding new tasks to T0 without catastrophic forgetting☆33Oct 20, 2022Updated 3 years ago
- ☆54May 8, 2023Updated 2 years ago
- ☆14May 10, 2021Updated 4 years ago
- BERT Probe: A python package for probing attention based robustness to character and word based adversarial evaluation. Also, with recipe…☆18Jun 24, 2022Updated 3 years ago
- phone inventory library☆17May 15, 2023Updated 2 years ago
- An easy way to start a python programming environment using GitHub Codespaces.☆15Sep 9, 2020Updated 5 years ago
- Fork of diux-dev/imagenet18☆16Oct 4, 2018Updated 7 years ago
- Unifew: Unified Fewshot Learning Model☆18Sep 10, 2021Updated 4 years ago
- The source code and dataset for our paper "Integrating Relation Constraints with Neural Relation Extractors" which is publicated at AAAI …☆15Mar 25, 2020Updated 5 years ago
- Code for the TACL paper "Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings"☆16Sep 8, 2020Updated 5 years ago
- Statistics on multilingual datasets☆17Jul 12, 2022Updated 3 years ago
- A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆18Nov 26, 2023Updated 2 years ago
- Source code for the NAACL 2021 paper: Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation☆15Jul 19, 2021Updated 4 years ago
- Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]☆39May 28, 2024Updated last year
- This repository contains source code for the paper "Language Model Prior for Low-Resource Neural Machine Translation"☆42Mar 16, 2021Updated 4 years ago
- Code for paper "CrossFit : A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)☆113Apr 28, 2022Updated 3 years ago
- ☆77Apr 29, 2024Updated last year
- code repo for EMNLP'21 Finding Counter-Interference Adapter for Multilingual Machine Translation☆18Oct 19, 2022Updated 3 years ago
- A simple algorithm to identify and correct for label shift.☆21Feb 4, 2018Updated 8 years ago
- Parameter Efficient Transfer Learning with Diff Pruning☆75Feb 3, 2021Updated 5 years ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆44Apr 7, 2024Updated last year
- Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE☆19Sep 22, 2021Updated 4 years ago
- Cross-lingual Language Model (XLM) pretraining and Model-Agnostic Meta-Learning (MAML) for fast adaptation of deep networks☆20Mar 26, 2021Updated 4 years ago
- m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter (EMNLP 2022)☆19Mar 28, 2023Updated 2 years ago
- PyTorch source code of NAACL 2021 paper "Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Tran…☆18Oct 18, 2022Updated 3 years ago
- ☆20Mar 22, 2024Updated last year