ant-louis / xm-retrievers
π Modular retrievers for zero-shot multilingual IR.
β26Updated 8 months ago
Related projects β
Alternatives and complementary repositories for xm-retrievers
- β15Updated 3 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 laβ¦β44Updated 11 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddingsβ17Updated 3 weeks ago
- INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.β22Updated last year
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrievalβ37Updated 2 weeks ago
- CLIR version of ColBERTβ64Updated last month
- SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.β42Updated last year
- Embedding Recycling for Language modelsβ38Updated last year
- β55Updated last year
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrievalβ27Updated 2 years ago
- β29Updated 9 months ago
- β14Updated 8 months ago
- β38Updated 6 months ago
- Ranking of fine-tuned HF models as base models.β35Updated last year
- β13Updated this week
- Using business-level retrieval system (BM25) with Python in just a few lines.β31Updated last year
- πΎ Universal, customizable and deployable fine-grained evaluation for text generation.β20Updated last year
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.β92Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning Pβ¦β34Updated last year
- Plug-and-play Search Interfaces with Pyserini and Hugging Faceβ32Updated last year
- β14Updated last month
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.β72Updated 2 years ago
- Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021β29Updated last year
- CCQA A New Web-Scale Question Answering Dataset for Model Pre-Trainingβ32Updated 2 years ago
- Retrieval-Augmented Generation battle!β44Updated last month
- β20Updated 3 years ago
- β45Updated 2 years ago
- β83Updated 2 months ago