asahi417 / lm-vocab-trimmerLinks
Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting irrelevant tokens from its vocabulary. This repository contains a python-library vocabtrimmer, that remove irrelevant tokens from a multilingual LM vocabulary for the target language.
☆56Updated last year
Alternatives and similar repositories for lm-vocab-trimmer
Users that are interested in lm-vocab-trimmer are comparing it to the libraries listed below
Sorting:
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆74Updated last year
- [TMLR'23] Contrastive Search Is What You Need For Neural Text Generation☆121Updated 2 years ago
- A Multilingual Replicable Instruction-Following Model☆95Updated 2 years ago
- Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023☆106Updated last year
- Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback☆97Updated 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.☆96Updated 2 years ago
- ☆101Updated 2 years ago
- MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning☆94Updated 2 years ago
- mSimCSE: Multilingual SimCSE☆34Updated 2 years ago
- ☆65Updated 2 years ago
- Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.☆117Updated 2 weeks ago
- Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arx…☆138Updated 2 years ago
- Code and data for the paper "Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?"☆25Updated 4 months ago
- ☆54Updated 2 years ago
- Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning☆30Updated 2 years ago
- A multilingual version of MS MARCO passage ranking dataset☆144Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated last year
- Dense hybrid representations for text retrieval☆63Updated 2 years ago
- The official repository for Efficient Long-Text Understanding Using Short-Text Models (Ivgi et al., 2022) paper☆70Updated 2 years ago
- ☆72Updated 2 years ago
- A multi-purpose toolkit for table-to-text generation: web interface, Python bindings, CLI commands.☆56Updated last year
- A extension of Transformers library to include T5ForSequenceClassification class.☆40Updated 2 years ago
- GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings☆44Updated last year
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆188Updated 3 months ago
- Using business-level retrieval system (BM25) with Python in just a few lines.☆31Updated 2 years ago
- Code and data accompanying the paper "TRUE: Re-evaluating Factual Consistency Evaluation".☆81Updated 3 months ago
- Pretraining Efficiently on S2ORC!☆170Updated last year
- ☆22Updated 2 years ago
- Code for Zero-Shot Tokenizer Transfer☆138Updated 9 months ago
- ☆39Updated last year