Stars
Training LLMs with QLoRA + FSDP
Build LLM-powered applications in Ruby
Language-Agnostic SEntence Representations
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Incremental Skip-gram Model with Negative Sampling
Word2Vec naïve version from scratch vs Word2Vec parallelized version.
Package for evaluating word embeddings
RiverText is a framework that standardizes the Incremental Word Embeddings proposed in the state-of-art. Please feel welcome to open an issue in case you have any questions or a pull request if you…
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
🍇 GRAPE is a Rust/Python Graph Representation Learning library for Predictions and Evaluations
A collection of ORM-style clients to public patent data
🔥 Use pre-trained models in PyTorch to extract vector embeddings for any image
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Header-only C++/python library for fast approximate nearest neighbors
Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.
FAst Lookups of Cosine and Other Nearest Neighbors (based on fast locality-sensitive hashing)
SIMD (SSE) population count --- https://0x80.pl/articles/sse-popcount.html
Javascript Canvas Library, SVG-to-Canvas (& canvas-to-SVG) Parser
Zest is a compression-based text classifier using Meta's Zstandard compression algorithm. Zest is language-agnostic and this approach simplifies configuration, avoids careful feature extraction and…
Datasets, SOTA results of every fields of Chinese NLP
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
Pytorch version of BERT-whitening
PyTorch code for SpERT: Span-based Entity and Relation Transformer