microsoft / AdaMix
This is the implementation of the paper AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning (https://arxiv.org/abs/2205.12410).
☆127Updated last year
Alternatives and similar repositories for AdaMix:
Users that are interested in AdaMix are comparing it to the libraries listed below
- Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models☆138Updated 2 years ago
- contrastive decoding☆190Updated 2 years ago
- ☆127Updated 2 years ago
- The original Backpack Language Model implementation, a fork of FlashAttention☆66Updated last year
- This is the oficial repository for "Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts" (EMNLP 2022)☆100Updated 2 years ago
- DSIR large-scale data selection framework for language model training☆242Updated 9 months ago
- ☆119Updated 6 months ago
- [TMLR'23] Contrastive Search Is What You Need For Neural Text Generation☆119Updated last year
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆130Updated 8 months ago
- This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).☆97Updated 2 years ago
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆48Updated last year
- One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning☆38Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆43Updated last year
- Code for paper 'Data-Efficient FineTuning'☆29Updated last year
- The official code of EMNLP 2022, "SCROLLS: Standardized CompaRison Over Long Language Sequences".☆70Updated last year
- Implementation of "The Power of Scale for Parameter-Efficient Prompt Tuning"☆164Updated 3 years ago
- A framework for few-shot evaluation of autoregressive language models.☆102Updated last year
- Retrieval as Attention☆83Updated 2 years ago
- A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.☆71Updated 5 months ago
- Efficient Transformers with Dynamic Token Pooling☆55Updated last year
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆96Updated last year
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆56Updated 4 months ago
- The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)☆157Updated 2 years ago
- Code for paper "UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning", ACL 2022☆59Updated 2 years ago
- ☆91Updated 7 months ago
- Progressive Prompts: Continual Learning for Language Models☆91Updated last year
- ☆22Updated last year
- MEND: Fast Model Editing at Scale☆241Updated last year
- Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.☆180Updated 2 years ago
- On Transferability of Prompt Tuning for Natural Language Processing☆97Updated 8 months ago