Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory β’ 8 items β’ Updated 3 days ago β’ 93
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval Paper β’ 2407.19669 β’ Published Jul 29, 2024 β’ 23
Lost in the Middle: How Language Models Use Long Contexts Paper β’ 2307.03172 β’ Published Jul 6, 2023 β’ 40
Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models Paper β’ 2307.11224 β’ Published Jul 20, 2023 β’ 6