RWKV-LM
by BlinkDL (personal account)
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… (description from the project’s GitHub page)
Repository facts
- Stars
- 14,748
- Forks
- 1,024
- Open issues and pull requests
- 159
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- BlinkDL · Personal account
- Created
- Aug 8, 2021
- Last push
- Sep 28, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 5,513: SuperBruceJia/EEG-DL
A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
1,173 starsPythonMITLast push Jul 20, 2025
Rank 867: BlinkDL/ChatRWKV
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
9,493 starsPythonApache-2.0Last push Jul 19, 2026
Rank 8,886: voidful/TextRL
Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
564 starsPythonMITLast push Apr 23, 2026
Rank 8,265: therealoliver/Deepdive-llama3-from-scratch
Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
629 starsJupyter NotebookMITLast push Feb 24, 2025
Rank 588: microsoft/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
13,860 starsPythonMITLast push Dec 17, 2024
Rank 963: OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
8,481 starsPythonApache-2.0Last push Aug 10, 2026