RWKV-LM license, foundation and stars

ML frameworks · Apache 2.0 (open source) · 14,774 stars

GitHubSuggest a correction

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.

More in ml frameworks

Apache 2.0201k starsTensorFlowAn Open Source Machine Learning Framework for Everyone.Google · +180 a week · v2.21.0, Mar 6, 2026Apache 2.0169k starsTransformersTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.Hugging Face · +337 a week · v5.17.0, Sep 9, 2026MIT112k starswhisperRobust Speech Recognition via Large-Scale Weak Supervision.OpenAI · +387 a weekBSD-style105k starsPyTorchTensors and Dynamic neural networks in Python with strong GPU acceleration.PyTorch Foundation · +311 a week · v2.14.0, Sep 2, 2026Apache 2.092.2k starsPaddleOCRTurn any PDF or image document into structured data for your AI.+333 a weekApache 2.091.4k starsopencvOpen Source Computer Vision Library.+77 a weekApache 2.079.2k starsunslothLocal UI to run and train LLMs and diffusion models.+407 a weekApache 2.077.4k starstesseractA machine learning library by tesseract-ocr, written in C++.+122 a week

Project	License	Stars	Per week	Latest release
TensorFlowAn Open Source Machine Learning Framework for Everyone.GoogleApache 2.0	Apache 2.0	201k	+180	v2.21.0Mar 6, 2026
TransformersTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.Hugging FaceApache 2.0	Apache 2.0	169k	+337	v5.17.0Sep 9, 2026
whisperRobust Speech Recognition via Large-Scale Weak Supervision.OpenAIMIT	MIT	112k	+387	-
PyTorchTensors and Dynamic neural networks in Python with strong GPU acceleration.PyTorch FoundationBSD-style	BSD-style	105k	+311	v2.14.0Sep 2, 2026
PaddleOCRTurn any PDF or image document into structured data for your AI.Apache 2.0	Apache 2.0	92.2k	+333	-
opencvOpen Source Computer Vision Library.Apache 2.0	Apache 2.0	91.4k	+77	-
unslothLocal UI to run and train LLMs and diffusion models.Apache 2.0	Apache 2.0	79.2k	+407	-
tesseractA machine learning library by tesseract-ocr, written in C++.Apache 2.0	Apache 2.0	77.4k	+122	-