Dense Vector Embeddings & Retrieval
7 repos
Production-ready models and frameworks for generating dense vector embeddings from text, enabling semantic search and retrieval tasks. This cluster centers on transformer-based embedding models (primarily BERT variants and specialized architectures like Contriever and E5) optimized for different scales and languages, along with supporting infrastructure for feature extraction and model quantization. Engineers here work with sentence-transformers and PyTorch to build retrieval systems, semantic similarity pipelines, and embedding-based applications across multilingual and resource-constrained contexts.
endpoints_compatible ·115
feature-extraction ·107
pytorch ·94
bert ·94
sentence-transformers ·82
sentence-similarity ·82
safetensors ·59
ja ·51
sentence-bert ·51
text-embeddings-inference ·43
