CPJKU / wechselLinks
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
☆82Updated 9 months ago
Alternatives and similar repositories for wechsel
Users that are interested in wechsel are comparing it to the libraries listed below
Sorting:
- Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning☆30Updated 2 years ago
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆32Updated 2 weeks 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.☆93Updated 2 years ago
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆101Updated last year
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 3 years ago
- Tutorial to pretrain & fine-tune a 🤗 Flax T5 model on a TPUv3-8 with GCP☆58Updated 2 years ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆72Updated last year
- ☆20Updated 2 years ago
- Code for ACL 2022 paper "Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation"☆30Updated 3 years ago
- ☆72Updated 2 years ago
- ☆65Updated last year
- NTREX -- News Test References for MT Evaluation☆83Updated last year
- Ensembling Hugging Face transformers made easy☆63Updated 2 years ago
- LTG-Bert☆33Updated last year
- ☆51Updated 2 years ago
- A tiny BERT for low-resource monolingual models☆31Updated 8 months ago
- Simple-to-use scoring function for arbitrarily tokenized texts.☆41Updated 4 months ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆58Updated last year
- Bicleaner fork that uses neural networks☆40Updated last week
- Implementation of the paper 'Sentence Bottleneck Autoencoders from Transformer Language Models'☆17Updated 3 years ago
- MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization☆74Updated 3 years ago
- Curriculum training☆18Updated 3 months ago
- ☆38Updated last year
- [TMLR'23] Contrastive Search Is What You Need For Neural Text Generation☆119Updated 2 years ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆76Updated 3 years ago
- Experiments on including metadata such as URLs, timestamps, website descriptions and HTML tags during pretraining.☆31Updated 2 years ago
- Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.☆109Updated 3 months ago
- A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆16Updated last year
- German Alpaca Dataset (Cleaned + Translated)☆25Updated 2 years ago
- Do Multilingual Language Models Think Better in English?☆41Updated last year