mrpeerat / SCT
SCT: An Efficient Self-Supervised Cross-View Training For Sentence Embedding (TACL)
☆14Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for SCT
- Implementation of ConGen: Unsupervised Control and Generalization Distillation For Sentence Representation (Finding of EMNLP 2022).☆21Updated last year
- Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.☆76Updated 2 months ago
- A Wikipedia-based summarization dataset☆13Updated last year
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆70Updated 8 months ago
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆29Updated last month
- A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆12Updated last year
- Code for the paper "Getting the most out of your tokenizer for pre-training and domain adaptation"☆13Updated 9 months ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆92Updated last year
- Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting ir…☆31Updated last month
- zero-vocab or low-vocab embeddings☆17Updated 2 years ago
- M2D2: A Massively Multi-domain Language Modeling Dataset (EMNLP 2022) by Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer☆55Updated 2 years ago
- Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback☆91Updated last year
- Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning☆29Updated last year
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆72Updated 2 years ago
- Auxiliary tasks for task-oriented dialogue systems. Published in ICNLSP'22 and indexed in the ACL Anthology.☆17Updated last year
- Framework for unified summarisation and evaluation of English documents using state-of-the-art models and measures.☆31Updated 6 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- Observe the slow deterioration of my mental sanity in the github commit history☆13Updated last year
- ☆27Updated last month
- Lightweight self-hosted span annotation tool☆23Updated this week
- Do Multilingual Language Models Think Better in English?☆41Updated last year
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 2 years ago
- ☆51Updated last year
- ☆73Updated last year
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆56Updated 5 months ago
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆97Updated 7 months ago
- A tiny BERT for low-resource monolingual models☆29Updated last month
- Hugging Face RoBERTa with Flash Attention 2☆19Updated last year
- Experiments with generating opensource language model assistants☆97Updated last year
- Code for Zero-Shot Tokenizer Transfer☆117Updated last month