CPJKU / wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
☆75Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for wechsel
- Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning☆29Updated 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
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 2 years 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
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆72Updated 2 years ago
- Code and data for the IWSLT 2022 shared task on Formality Control for SLT☆21Updated last year
- LTG-Bert☆29Updated 10 months ago
- Tools for managing datasets for governance and training.☆78Updated 3 weeks ago
- Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.☆90Updated last month
- This repository contains a demonstrative implementation for pooling-based models, e.g., DeepPyramidion complementing our paper "Sparsifyi…☆14Updated 2 years ago
- UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specifi…☆30Updated last year
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆56Updated 5 months ago
- ☆73Updated 3 years ago
- Do Multilingual Language Models Think Better in English?☆41Updated last year
- A software for transferring pre-trained English models to foreign languages☆18Updated last year
- Reduce the size of pretrained Hugging Face models via vocabulary trimming.☆43Updated last year
- Bicleaner fork that uses neural networks☆38Updated 3 months ago
- ☆21Updated 3 months ago
- Experiments on including metadata such as URLs, timestamps, website descriptions and HTML tags during pretraining.☆30Updated last year
- Curriculum training☆16Updated 2 months ago
- ☆16Updated last year
- Simple-to-use scoring function for arbitrarily tokenized texts.☆32Updated 3 weeks ago
- This repositary hosts my experiments for the project, I did with OffNote Labs.☆11Updated 3 years ago
- Research code for the paper "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models"☆26Updated 3 years ago
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆96Updated 7 months ago
- Tutorial to pretrain & fine-tune a 🤗 Flax T5 model on a TPUv3-8 with GCP☆58Updated 2 years ago
- ☆51Updated last year
- M2D2: A Massively Multi-domain Language Modeling Dataset (EMNLP 2022) by Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer☆55Updated 2 years ago
- Ensembling Hugging Face transformers made easy☆62Updated last year