๐Ÿ† #104 overall#36 of 601 in Language Models๐Ÿ”ฅ active this week

BlinkDL /RWKV-LM

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.

$ git clone https://github.com/BlinkDL/RWKV-LM.git
GitHub social preview for BlinkDL/RWKV-LM
Stars
14.7K
14,718
Forks
1K
1,021
Language
Python
License
Apache-2.0
Created
Aug 8, 2021
5.1 years old
Last push
Sep 21, 2026
๐Ÿ”ฅ this week

Categories

GitHub topics

More in Language Models

Language Models

microsoft/LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

PythonMITupdated Dec 17, 2024
GitHub โ†—โ˜… 13.8Kโ‘‚ 929
Language Models

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)

๐Ÿง  Natural Language Processing
PythonMITupdated Apr 23, 2026
GitHub โ†—โ˜… 564โ‘‚ 61
Language Models

rasbt/LLMs-from-scratch๐Ÿ”ฅ active

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

โœ‚๏ธ Tokenization & Preprocessing๐Ÿง  Natural Language Processing
Jupyter NotebookOtherupdated Sep 22, 2026
GitHub โ†—โ˜… 105.5Kโ‘‚ 16.2K
Language Models

OptimalScale/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

PythonApache-2.0updated Aug 10, 2026
GitHub โ†—โ˜… 8.5Kโ‘‚ 822
Language Models

raiyanyahya/how-to-train-your-gpt

Build a modern LLM from scratch. Every line commented. Explained like we are five.

๐Ÿง  Natural Language Processing
Jupyter NotebookMITupdated Aug 30, 2026
GitHub โ†—โ˜… 3.4Kโ‘‚ 419

Data from GitHub ยท snapshot Sep 24, 2026