jxmorris12 / bm25_ptLinks
minimal pytorch implementation of bm25 (with sparse tensors)
☆104Updated 3 months ago
Alternatives and similar repositories for bm25_pt
Users that are interested in bm25_pt are comparing it to the libraries listed below
Sorting:
- The official code repo for "Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations".☆85Updated 2 years ago
- Model implementation for the contextual embeddings project☆40Updated 7 months ago
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆191Updated 6 months ago
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆82Updated last year
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆74Updated this week
- ☆90Updated 6 months ago
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆155Updated 6 months ago
- ☆38Updated last year
- Crispy reranking models by Mixedbread☆45Updated 4 months ago
- PyTorch implementation for MRL☆20Updated last year
- Pre-train Static Word Embeddings☆94Updated 4 months ago
- NLP with Rust for Python 🦀🐍☆70Updated 8 months ago
- experiments with inference on llama☆103Updated last year
- ☆52Updated 6 months ago
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆61Updated last year
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆22Updated 7 months ago
- 🚢 Data Toolkit for Sailor Language Models☆95Updated 11 months ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated 2 years ago
- Notebooks for training universal 0-shot classifiers on many different tasks☆138Updated last year
- [EMNLP 2024] A Retrieval Benchmark for Scientific Literature Search☆102Updated last year
- ☆59Updated last year
- Supercharge huggingface transformers with model parallelism.☆77Updated 6 months ago
- ☆53Updated 11 months ago
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆202Updated last year
- CLIR version of ColBERT☆73Updated 7 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated 2 years ago
- Retrieval Augmented Generation Generalized Evaluation Dataset☆61Updated 6 months ago
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆61Updated 6 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated last year
- Pretraining Efficiently on S2ORC!☆179Updated last year