baaivision/EVA
quality grade D, 41 out of 100EVA Series: Visual Representation Fantasies from BAAI
- stars
- 2.7k
- stars gained this week
- —this week
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Text and multimodal embedding models, rerankers and representation learning.
Signals: embeddings, sentence-embeddings, text-embeddings, sentence-transformers, reranking, representation-learning, contrastive-learning
71 results
EVA Series: Visual Representation Fantasies from BAAI
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
A curated list of research papers in Sentence Reprsentation Learning and a sts leaderboard of sentence embeddings.
The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!
Keyphrase or Keyword Extraction 基于预训练模型的中文关键词抽取方法(论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model 的中文版代码)
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences
Compute Sentence Embeddings Fast!
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
text2vec, text to vector. 文本向量表征工具,把文本转化为向量矩阵,实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型,开箱即用。
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Retrieval and Retrieval-augmented LLMs
Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
unified embedding model
Fast State-of-the-Art Static Embeddings
Efficient few-shot learning with Sentence Transformers
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Train Models Contrastively in Pytorch
DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
A list of contrastive Learning papers
[Survey] Masked Modeling for Self-supervised Representation Learning on Vision and Beyond (https://arxiv.org/abs/2401.00897)
[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning
24,523 repositories in the index in total.