recombee / CompresSAELinks
Sparse Embedding Compression for Scalable Retrieval in Recommender Systems
☆28Updated 5 months ago
Alternatives and similar repositories for CompresSAE
Users that are interested in CompresSAE are comparing it to the libraries listed below
Sorting:
- Model implementation for the contextual embeddings project☆36Updated 5 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆66Updated last month
- CLIR version of ColBERT☆74Updated 4 months ago
- Python library to use Pleias-RAG models☆66Updated 6 months ago
- SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.☆47Updated 2 years ago
- Crispy reranking models by Mixedbread☆38Updated 2 months ago
- Code of fine-tuning neural sparse models and training from scratch. #SIGIR2025☆16Updated this week
- 🌏 Modular retrievers for zero-shot multilingual IR.☆28Updated last year
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆58Updated last year
- Official Repository for "Hypencoder: Hypernetworks for Information Retrieval"☆31Updated last month
- ☆51Updated 9 months ago
- Faster Learned Sparse Retrieval with Block-Max Pruning. ACM SIGIR 2024.☆31Updated last month
- ☆52Updated 3 months ago
- Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.☆88Updated this week
- Datamodels for hugging face tokenizers☆86Updated last week
- Pre-train Static Word Embeddings☆90Updated 2 months ago
- A massively multilingual modern encoder language model☆107Updated last month
- Improving Text Embedding of Language Models Using Contrastive Fine-tuning☆65Updated last year
- ☆46Updated last month
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆169Updated 6 months ago
- Implementation of "Efficient Multi-vector Dense Retrieval with Bit Vectors", ECIR 2024☆66Updated 3 weeks ago
- ☆18Updated last year
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆190Updated last year
- 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
- My NER Experiments with ModernBERT and Ettin☆22Updated 4 months ago
- Optimus is a flexible and scalable framework built to train language models efficiently across diverse hardware configurations, including…☆67Updated 4 months ago
- Generalist and Lightweight Model for Text Classification☆164Updated 5 months ago
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆33Updated last month
- A list of multi-vector retrieval resources☆14Updated last year
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆33Updated last year