47,133 repositories indexed
601–624 of 5,362 · Most stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
NLTK Source
TranslatedLlama Chinese community: compiles the latest Llama learning materials in real time and builds the best open-source ecosystem of Chinese Llama large models, fully open source and commercially usable
A Conversational Speech Generation Model
Image augmentation for machine learning experiments.
Open-source, secure environment with real-world tools for enterprise-grade agents.
DALL·E Mini - Generate images from a text prompt
A list of all named GANs!
100 numpy exercises (with solutions)
The pytest framework makes it easy to write small tests, yet scales to support complex functional testing
FauxPilot - an open-source alternative to GitHub Copilot server
Personal memory across agents
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Clone of the Age of Empires II engine 🚀
The repository host gives no description.
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
ChatterBot is a machine learning, conversational dialog engine for creating chat bots
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
StyleGAN - Official TensorFlow Implementation
A framework for few-shot evaluation of language models.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption