ielab / StarbucksLinks
Starbucks: Improved Training for 2D Matryoshka Embeddings
☆21Updated 2 months ago
Alternatives and similar repositories for Starbucks
Users that are interested in Starbucks are comparing it to the libraries listed below
Sorting:
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated last year
- Embedding Recycling for Language models☆39Updated 2 years ago
- ☆46Updated 3 years ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆29Updated 2 years ago
- ☆14Updated 11 months ago
- ☆54Updated 2 years ago
- INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.☆24Updated last year
- Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders☆18Updated 3 months ago
- Code for SaGe subword tokenizer (EACL 2023)☆26Updated 9 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆63Updated 2 weeks ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated 2 years ago
- SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.☆47Updated 2 years ago
- Official Repository for "Hypencoder: Hypernetworks for Information Retrieval"☆29Updated 6 months ago
- One-stop shop for running and fine-tuning transformer-based language models for retrieval☆59Updated this week
- Source code and data for Like a Good Nearest Neighbor☆30Updated 8 months ago
- This repository contains the code for the paper 'PARM: Paragraph Aggregation Retrieval Model for Dense Document-to-Document Retrieval' pu…☆41Updated 3 years ago
- SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batchi…☆33Updated last year
- ☆28Updated last year
- Model implementation for the contextual embeddings project☆36Updated 3 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.☆95Updated 2 years ago
- Code release for Type-Aware Bi-Encoders for Open-Domain Entity Retrieval☆19Updated 2 years ago
- Repo for ICML23 "Why do Nearest Neighbor Language Models Work?"☆59Updated 2 years ago
- ☆10Updated 11 months ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last year
- 🌏 Modular retrievers for zero-shot multilingual IR.☆28Updated last year
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval☆52Updated 3 months ago
- ☆14Updated this week
- Few-shot Learning with Auxiliary Data☆31Updated last year
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆32Updated last year
- ☆86Updated 5 months ago