Repository Index

Topic Modelling for Humans

• gensim
• topic-modeling
• information-retrieval
• machine-learning

Retrieval and Retrieval-augmented LLMs

• embeddings
• information-retrieval
• llm
• sentence-embeddings

Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.

• metric-learning
• deep-learning
• computer-vision
• machine-learning

Translatedtext2vec, text to vector. A text vector representation tool that converts text into vector matrices. It implements text representation and text similarity calculation models such as Word2Vec, RankBM25, Sentence-BERT, and CoSENT, and works out of the box.

• similarity
• nlp
• text-similarity
• text2vec

Representation learning on large graphs using stochastic graph convolutions.

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

• machine-learning
• convolutional-networks
• embedding-vectors
• embeddings

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

• colpali
• information-retrieval
• retrieval-augmented-generation
• vision-language-model

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

• embeddings
• information-retrieval
• language-model
• text-classification

WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.

• embedding-models
• multimodal
• multimodal-llm

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

A fast, efficient universal vector embedding utility package.

• python
• natural-language-processing
• nlp
• machine-learning

一行代码使用BERT生成句向量，BERT做文本分类、文本相似度计算

Tensorflow implementation of contextualized word representations from bi-directional language models

repository for Publicly Available Clinical BERT Embeddings

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Learning Heterogeneous Tactile Representation for General Dexterous Manipulation