An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
- deepspeed-library
- gpt-3
- transformers
- language-model
80,339 visible repositories in the index
697–720 of 4,870 · Most stars
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
PRINTFILM: AI short-video marketing and AI short-drama creation platform
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Minimal PyTorch implementation of YOLOv3
Infinite Photorealistic Worlds using Procedural Generation
Python Data. Leaflet.js Maps.
File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
Implementation of Graph Convolutional Networks in TensorFlow
Centralized network visibility and continuous asset discovery. Monitor devices, detect change, and stay aware across distributed networks.
TripoSR: Fast 3D Object Reconstruction from a Single Image
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
Very efficient backup system based on the git packfile format, providing fast incremental saves and global deduplication (among and within files, including virtual machine images). Please post problems or patches to the mailing list for discussion (see the end of the README below).
Collect your thoughts and notes without leaving the command line.
TranslatedSome scripts and improvement-idea code for object detection; see readme.md for details
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
TranslatedDeepAudit: An AI hacker team for everyone, putting vulnerability discovery within reach. Beginners can deploy and run it with one click, with autonomous collaborative auditing + automated sandbox PoC verification. Supports private deployment with Ollama and one-click report generation. Supports relay stations. Making security no longer expensive and auditing no longer complicated.
OpenVLA: An open-source vision-language-action model for robotic manipulation.
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Self hosted FLOSS fitness/workout, nutrition and weight tracker