State-of-the-Art Embeddings, Retrieval, and Reranking
Repository Index
103,113 visible repositories in the index
1–13 of 13 · Most stars
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Source code for Twitter's Recommendation Algorithm
ImageBind One Embedding Space to Bind Them All
Open-source inference server and production cluster for all the models your agent needs.
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
- embeddings
- openai
- rag
- retrieval
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
Fast State-of-the-Art Static Embeddings
- embeddings
- machine-learning
- model2vec
- nlp
Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"
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
Things you can do with the token embeddings of an LLM
Implementation of the node2vec algorithm.
- machine-learning-algorithms
- embeddings
- deep-learning
Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.
- artificial-intelligence
- clip
- pathology
- vision-and-language