DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Repository Index
132,241 visible repositories in the index
1–24 of 37 · Most stars
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
- knowledge-graph
- large-language-model
- logical-reasoning
- multi-hop-question-answering
Build effective agents using Model Context Protocol and simple workflow patterns
PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
- pdfgpt
- chatpdf
- chatwithpdf
Machine Learning meets ketosis: how to effectively lose weight
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
- controlnet
- knowledge-distillation
- pose-estimation
- stable-diffusion-webui
[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"
- deep-learning
- forecasting
- forecasting-model
- linear-models
Effective Python: Third Edition — Source Code and Errata for the Book
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
- embodied-ai
- robotics
- vision-language-action-model
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)
- time-series-forecasting
- transformer
ClatScope Info Tool – The best and most versatile OSINT utility for retrieving geolocation, DNS, WHOIS, phone, email, data breach information and much more (70+ features). Perfect for investigators, pentesters, or anyone looking for an effective reconnaissance / OSINT tool.
- intelligence
- investigation
- osint
- osint-python
[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability.
Code Sample of Book "Effective Python: 59 Specific Ways to Write Better Pyton" by Brett Slatkin
- tricks
- python-3
- python
- effective-python
Course demos and handouts for Talk Python's Effective PyCharm course
- python
- python3
- pycharm
- ide
Benchmark for vector databases.
- benchmark
- performance
- vector-database
- vector-search
Contextualise is an effective tool particularly suited for organising information-heavy projects and activities consisting of unstructured and widely diverse data and information resources
- knowledge-graph
- flask-application
- python3
- metamodel
A graph-based tool for visualizing effective access and resource relationships in AWS environments.
- aws
- aws-security
- graph-theory
- pentesting
About Osintgraph is an open-source tool that collects Instagram data, followers, and followees, storing them in Neo4j. It helps you easily map and analyze a target's social network, revealing interests, connections, and affiliations for effective OSINT.
A simple tutorial about effectively using pdb
Python library for building highly effective data science workflows
A simple and effective LLM pruning approach.
- large-language-models
- network-pruning
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
- efficiency
- large-language-models
- rag
- search-agent
Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"
- pytorch
- cvpr2019
- loss-functions
- deep-learning