Real-time Voice Activity Detection (VAD) with some example use case like simple voice bot and live transcription (realtime transcription)

Voice activity detector (VAD) for the browser with a simple API

Voice Activity Detection (VAD) AudioWorklet

LLM training in simple, raw C/CUDA

The Abstraction and Reasoning Corpus

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

Python library that allows you to get structured responses in the form of Pydantic models and Python types from Anthropic, Google Vertex AI and OpenAI models

Embeddings for the Slovenian language

Carrot2: Text Clustering Algorithms and Applications

State-of-the-Art Text Embeddings

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

Tweet Generation with Huggingface

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

A fast, GPU-ready bezier-curve implementation

Tensors and Dynamic neural networks in Python with strong GPU acceleration

AlphaFold2 and RoseTTAFold predictions of the SARS-CoV-2 B.1.1.529 variant Spike protein with HADDOCK antibody interactions

Repository for suggesting new lineages that should be added to the current scheme

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations

A data preprocessing package for time series data. Design for machine learning and deep learning.

A lightweight web application for brushing labels onto time series data; useful for building training sets.

A Swift wrapper for fastbpe

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training