CPJKU / wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
☆77Updated 5 months ago
Alternatives and similar repositories for wechsel:
Users that are interested in wechsel are comparing it to the libraries listed below
- Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning☆29Updated 2 years ago
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆29Updated 4 months ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆70Updated 11 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.☆93Updated 2 years ago
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 3 years ago
- Curriculum training☆16Updated last month
- Ensembling Hugging Face transformers made easy☆63Updated 2 years ago
- NTREX -- News Test References for MT Evaluation☆81Updated 8 months ago
- Code and data for the IWSLT 2022 shared task on Formality Control for SLT☆21Updated last year
- ☆20Updated 2 years ago
- LTG-Bert☆29Updated last year
- Personal information identification standard☆19Updated last year
- ☆73Updated last year
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆99Updated 10 months ago
- Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.☆98Updated 2 months ago
- Tutorial to pretrain & fine-tune a 🤗 Flax T5 model on a TPUv3-8 with GCP☆58Updated 2 years ago
- ☆74Updated 3 years ago
- This repository contains a demonstrative implementation for pooling-based models, e.g., DeepPyramidion complementing our paper "Sparsifyi…☆14Updated 2 years ago
- Research code for the paper "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models"☆26Updated 3 years ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆74Updated 3 years ago
- ☆65Updated last year
- German small and large versions of GPT2.☆20Updated 2 years ago
- ☆51Updated last year
- UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specifi…☆30Updated 2 years ago
- Megatron LM 11B on Huggingface Transformers☆27Updated 3 years ago
- Code for ACL 2022 paper "Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation"☆30Updated 2 years ago
- A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆14Updated last year
- Tool to fix bitexts and tag near-duplicates for removal☆29Updated 2 weeks ago
- This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalenc…☆53Updated 6 months ago
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆56Updated 8 months ago