2 repository-uri
Awesome GitHub RepositoriesTraining Data Compression
Compression techniques specifically designed to reduce the footprint of training datasets.
Distinct from Video Processing: Distinct from general video codecs by focusing on reducing training costs while preserving quality.
Explore 2 awesome GitHub repositories matching part of an awesome list · Training Data Compression. Refine with filters or upvote what's useful.
Awesome Training Data Compression GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- pku-yuangroup/open-sora-plan
PKU-YuanGroup/Open-Sora-Plan
12,163Vezi pe GitHubOpen-Sora-Plan is a text-to-video framework and distributed video training system. It utilizes a diffusion transformer architecture and large language model components to transform written descriptions or image prompts into high-quality video sequences. The system features a distributed infrastructure designed for large-scale video training and inference. It employs sequence parallelism to split high-resolution or long-duration video samples across multiple GPUs and uses a sparse attention mechanism to increase processing speed. The project includes capabilities for both text-to-video and im
Reduces the size of video frames to lower training costs while preserving high image quality.
Python - facebookresearch/starspace
facebookresearch/Starspace
3,954Vezi pe GitHubStarspace is a vector embedding framework designed for training high-dimensional representations of text and images. It functions as a machine learning system for neural ranking, text classification, and knowledge graph embedding, mapping different object types into a shared numerical space to facilitate retrieval and prediction tasks. The system includes specialized tools for knowledge graph completion and link prediction by representing entities and their relationships within a multi-relational vector space. It further provides capabilities for semantic content recommendation and large-scal
Supports reading training data from compressed formats to minimize the disk footprint of large datasets.
C++
