mlcommons / dynabench
☆19Updated last week
Related projects ⓘ
Alternatives and complementary repositories for dynabench
- Code for SaGe subword tokenizer (EACL 2023)☆22Updated last month
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆17Updated 3 weeks ago
- Documentation effort for the BookCorpus dataset☆31Updated 3 years ago
- Tokenization across languages. Useful as preprocessing for subword tokenization.☆22Updated last year
- Source code and data for Like a Good Nearest Neighbor☆28Updated 9 months ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated last year
- SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batchi…☆31Updated 5 months ago
- SeqScore: Scoring for named entity recognition and other sequence labeling tasks☆20Updated 3 weeks ago
- LTG-Bert☆29Updated 10 months ago
- Efficiently computing & storing token n-grams from large corpora☆15Updated last month
- Hugging Face and Pyserini interoperability☆19Updated last year
- Simple-to-use scoring function for arbitrarily tokenized texts.☆31Updated 2 weeks ago
- Scripts supporting the development and serving the Roots Search Tool - https://hf.co/spaces/bigscience-data/roots-search☆10Updated last year
- An unofficial implementation of the Infini-gram model proposed by Liu et al. (2024)☆24Updated 4 months ago
- Ranking of fine-tuned HF models as base models.☆35Updated last year
- Ludwig benchmark☆19Updated 2 years ago
- ☆14Updated last month
- Code for "CyberWallE at SemEval-2020 Task 11: An Analysis of Feature Engineering for Ensemble Models for Propaganda Detection" (V. Blasch…☆9Updated 4 years ago
- Experiments on including metadata such as URLs, timestamps, website descriptions and HTML tags during pretraining.☆30Updated last year
- Embedding Recycling for Language models☆38Updated last year
- This repository contains code and data for the EMNLP 2022 paper "CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about…☆9Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆44Updated 11 months ago
- Library for fast text representation and classification.☆28Updated 10 months ago
- Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning☆34Updated 7 months ago
- ☆16Updated last year
- Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex progr…☆23Updated 2 months ago
- ☆27Updated last year
- ☆19Updated last year
- [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"☆28Updated 3 weeks ago
- ☆38Updated 6 months ago
- Few-shot Learning with Auxiliary Data☆26Updated 11 months ago