embeddinggemma-300m

Model · Sentence similarity

bge-m3

Beijing Academy of Artificial Intelligence

For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. Some suggestions for retrieval pipeline in RAG We recommend to use the following pipeline: hybrid retrieval + re-ranking. - Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings. To…

Model · Sentence similarity

bge-small-en-v1.5-onnx-Q

Qdrant

Quantized ONNX port of BAAI/bge-small-en-v1.5 for text classification and similarity searches. Here's an example of performing inference using the model with FastEmbed.

Model · Sentence similarity

all-MiniLM-L6-v2-onnx

Qdrant

ONNX port of sentence-transformers/all-MiniLM-L6-v2 for text classification and similarity searches. Here's an example of performing inference using the model with FastEmbed.

Model · Sentence similarity

bm25

Qdrant

Repository with files to perform BM25 searches with FastEmbed. BM25 (Best Matching 25) is a ranking function used by search engines to estimate the relevance of documents to a given search query. This model is supposed to be used with Qdrant. Vectors have to be configured with Modifier.IDF. Here's an example of BM25 with FastEmbed.

Model · Sentence similarity

Splade_PP_en_v1

Qdrant

ONNX port of prithivida/SpladePPenv1 for text classification and similarity searches. Here's an example of performing inference using the model with FastEmbed.

ViDense is a VietNamese Embedding Model. Fine-tuned and enhanced with tailored methods, ViDense incorporates advanced techniques to optimize performance for text embeddings in various applications. Trained for 10 epochs with a train batch size of 2048. Utilizes a 3-phase training approach, where the best checkpoint from each phase serves as the base model for the next. Momentum Encoder: Incorporates MoCo (Momentum Contrast) to enhance in-batch negative sampling. of positives as relevant to the anchor, it reranks the corpus using the Spearman metric and integrates Spearman weights into the loss calculation for improved ranking. Below is a comparision table of the results I achieved compared…