A LLM trained only on data from certain time periods to reduce modern bias
Repository Index
89,572 visible repositories in the index
5,737–5,760 of 12,700 · Most stars
Keras Temporal Convolutional Network. Supports Python and R.
- keras
- tcn
- recurrent-neural-networks
- deep-learning
Управление Яндекс.Станцией и другими устройствами умного дома с Алисой из Home Assistant
- home-assistant
- yandex-station
- hacs
- tts
Windows的开源强力清理工具,可扫描并清理全盘中的垃圾文件、大文件、重复文件及系统残留等
an open-source, low-cost DIY 360° LiDAR scanner and panoramic 3D reconstruction system.
万象拼音数据与工具中心: 简繁扩展词库/声调编码/声调标注工具链/万象更新工具链/Rime语法模型
- dictionary
- grammar
- language-model
- rime
Reusable, generic mixins for Django
- django
- python
- django-braces
- class-based
A fully configurable and extendable Bash obfuscation framework. This tool is intended to help both red team and blue team.
Codebase for Berkeley Humanoid Lite
- berkeley-humanoids
Find web directories without bruteforce
- pentesting
- security
- security-tools
- websec
Bilibili视频转文字,一步到位,输入链接即可使用
A Python SOAP client
- python
- soap
- soap-client
- wsdl
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
- chatbot
- clip
- computer-vision
- dino
django-tables2 - An app for creating HTML tables
- django
- python
- tableview
- tables
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
- yolov4
- scaled-yolov4
- yolov4-csp
- darknet
Chai-1, SOTA model for biomolecular structure prediction
A library for graph deep learning research
- deep-learning
- graph-neural-network
- graph-generation
- explainable-ml
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
- acoustics
- room-impulse-response
- image-source-model
- beamforming
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形,设置面部区域可配置的增强方式进行合成唇形(人脸)区域画面增强,提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧,补充帧间合成唇形的动作过渡,使合成的唇形更为流畅、真实以及自然。
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Decrypted content of odd.tar.xz.gpg, swift.tar.xz.gpg and windows.tar.xz.gpg
- shadowbrokers
- nsa
- equationgroup
CUDA Accelerated Robot Library