This is a text embedding model converted to the MLX format, derived from Google's EmbeddingGemma-300m model. It is specifically designed for sentence similarity calculation and text embedding tasks. The model uses BF16 precision and is suitable for efficient inference on Apple chip devices.

Natural Language ProcessingSentence-transformers

EmbeddingGemma-300m-8bit is a sentence similarity model implemented based on the sentence-transformers library. It supports running in MLX format and is specifically designed for calculating sentence embeddings and similarities. This model is converted from the original model and provides efficient text feature extraction capabilities.

Natural Language ProcessingSentence-transformers

EmbeddingGemma 300M 4bit is a lightweight text embedding model developed by Google, specifically optimized for the MLX framework. This model can convert text into high-quality vector representations and is suitable for various natural language processing tasks, especially sentence similarity calculation and feature extraction.

Natural Language ProcessingSentence-transformers

embeddinggemma-300m-qat-q8_0 GGUF is a quantized version based on the Google embeddinggemma-300m model, specifically designed for feature extraction and sentence similarity calculation. This model has been quantized and optimized to significantly reduce the model size and inference overhead while maintaining high accuracy.

Natural Language ProcessingSentence-transformers

embeddinggemma-300M is a lightweight text embedding model optimized through quantization. Based on Google's embeddinggemma architecture, it uses QAT (Quantization-Aware Training) and Q4_0 quantization techniques, with 300M parameters. This model is specifically designed to generate high-quality text embedding vectors and supports tasks such as sentence similarity calculation and feature extraction.

Natural Language ProcessingSentence-transformers