Git Stars Git Stars

#gpt-2 Repositories

Discover 30 active open source GitHub repositories tagged with #gpt-2, accumulating 111,632 total stars (averaging 3,721 stars per project). Leading this topic is BlinkDL/RWKV-LM with 14,786 stars.

30
Total Repositories
111,632
Total Stars
3,721
Avg Stars/Repo
1
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.

BlinkDL
โญ 14,786 Python ๐Ÿ‘ค BlinkDL User ๐Ÿ• Updated 2026-11-04 ๐Ÿ“… Created 2021-08-08
2
microsoft/LoRA

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

microsoft
โญ 13,111 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2024-12-17 ๐Ÿ“… Created 2021-06-18
3
NielsRogge/Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

NielsRogge
โญ 11,787 Jupyter Notebook ๐Ÿ‘ค NielsRogge User ๐Ÿ• Updated 2026-09-17 ๐Ÿ“… Created 2020-08-31
4
codota/TabNine

AI Code Completions

codota
โญ 10,775 Shell ๐Ÿ‘ค codota Organization ๐Ÿ• Updated 2025-09-04 ๐Ÿ“… Created 2018-11-06
5
FoundationVision/VAR

[NeurIPS 2024 Best Paper Award][GPT beats diffusion๐Ÿ”ฅ] [scaling laws in visual generation๐Ÿ“ˆ] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

FoundationVision
โญ 8,766 Jupyter Notebook ๐Ÿ‘ค FoundationVision Organization ๐Ÿ• Updated 2025-11-10 ๐Ÿ“… Created 2024-04-01
6
Morizeyao/GPT2-Chinese

Chinese version of GPT2 training code, using BERT tokenizer.

Morizeyao
โญ 7,609 Python ๐Ÿ‘ค Morizeyao User ๐Ÿ• Updated 2024-04-25 ๐Ÿ“… Created 2019-05-31
7
lonePatient/awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models, High-Quality Chinese Pretrained Models & Large Models & Multimodal Models & Large Language Models Collection

lonePatient
โญ 5,618 Python ๐Ÿ‘ค lonePatient User ๐Ÿ• Updated 2026-08-30 ๐Ÿ“… Created 2019-05-25
8
Turing-Project/WriteGPT

Developed by Turing's Cat, the first generation of creative AI, based on open-source GPT2.0 | Scalable, evolvable

Turing-Project
โญ 5,318 Python ๐Ÿ‘ค Turing-Project Organization ๐Ÿ• Updated 2024-03-31 ๐Ÿ“… Created 2020-09-29
9
dbiir/UER-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

dbiir
โญ 3,102 Python ๐Ÿ‘ค dbiir Organization ๐Ÿ• Updated 2024-05-09 ๐Ÿ“… Created 2019-04-10
10
guillaume-be/rust-bert

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2, ...)

guillaume-be
โญ 3,092 Rust ๐Ÿ‘ค guillaume-be User ๐Ÿ• Updated 2026-01-13 ๐Ÿ“… Created 2020-01-25
11
stochasticai/xTuring

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

stochasticai
โญ 2,680 Python ๐Ÿ‘ค stochasticai Organization ๐Ÿ• Updated 2026-11-05 ๐Ÿ“… Created 2023-03-19
12
asyml/texar

Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

asyml
โญ 2,391 Python ๐Ÿ‘ค asyml Organization ๐Ÿ• Updated 2026-07-21 ๐Ÿ“… Created 2017-07-22
13
BrikerMan/Kashgari

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

BrikerMan
โญ 2,387 Python ๐Ÿ‘ค BrikerMan User ๐Ÿ• Updated 2024-09-03 ๐Ÿ“… Created 2019-01-19
14
guinmoon/LLMFarm

llama and other large language models on iOS and MacOS offline using GGML library.

guinmoon
โญ 2,081 C ๐Ÿ‘ค guinmoon User ๐Ÿ• Updated 2026-01-30 ๐Ÿ“… Created 2023-06-14
15
VHellendoorn/Code-LMs

Guide to using pre-trained large language models of source code

VHellendoorn
โญ 1,840 Python ๐Ÿ‘ค VHellendoorn User ๐Ÿ• Updated 2024-07-07 ๐Ÿ“… Created 2021-11-25
16
FoundationVision/Infinity

[CVPR 2025 Oral]Infinity โˆž : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

FoundationVision
โญ 1,595 Python ๐Ÿ‘ค FoundationVision Organization ๐Ÿ• Updated 2026-04-16 ๐Ÿ“… Created 2024-11-29
17
codota/tabnine-vscode

Visual Studio Code client for Tabnine. https://marketplace.visualstudio.com/items?itemName=TabNine.tabnine-vscode

codota
โญ 1,433 TypeScript ๐Ÿ‘ค codota Organization ๐Ÿ• Updated 2026-10-01 ๐Ÿ“… Created 2018-10-01
18
explosion/spacy-transformers

๐Ÿ›ธ Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

explosion
โญ 1,411 Python ๐Ÿ‘ค explosion Organization ๐Ÿ• Updated 2026-11-03 ๐Ÿ“… Created 2019-07-26
19
rmokady/CLIP_prefix_caption

Simple image captioning model

rmokady
โญ 1,407 Jupyter Notebook ๐Ÿ‘ค rmokady User ๐Ÿ• Updated 2024-06-09 ๐Ÿ“… Created 2021-09-16
โญ 1,258 Python ๐Ÿ‘ค google-deepmind Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2024-10-23
21
SkalskiP/vlms-zero-to-hero

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

SkalskiP
โญ 1,172 Jupyter Notebook ๐Ÿ‘ค SkalskiP User ๐Ÿ• Updated 2025-01-23 ๐Ÿ“… Created 2024-12-20
22
shyamsn97/mario-gpt

[Neurips 2023] Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models" https://arxiv.org/abs/2302.05981

shyamsn97
โญ 1,143 Python ๐Ÿ‘ค shyamsn97 User ๐Ÿ• Updated 2024-07-22 ๐Ÿ“… Created 2023-02-14
23
cedrickchee/awesome-transformer-nlp

A curated list of NLP resources focused on Transformer networks, attention mechanism, GPT, BERT, ChatGPT, LLMs, and transfer learning.

cedrickchee
โญ 1,124 ๐Ÿ‘ค cedrickchee User ๐Ÿ• Updated 2024-10-27 ๐Ÿ“… Created 2019-01-13
24
Tencent/TencentPretrain

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

Tencent
โญ 1,086 Python ๐Ÿ‘ค Tencent Organization ๐Ÿ• Updated 2024-08-04 ๐Ÿ“… Created 2022-09-26
26
turtlesoupy
โญ 1,022 Python ๐Ÿ‘ค turtlesoupy User ๐Ÿ• Updated 2026-06-17 ๐Ÿ“… Created 2020-03-09
27
niieani/gpt-tokenizer

The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features.

niieani
โญ 862 TypeScript ๐Ÿ‘ค niieani User ๐Ÿ• Updated 2026-11-10 ๐Ÿ“… Created 2023-03-22
28
BurhanUlTayyab/GPTZero

An open-source implementation of GPTZero

BurhanUlTayyab
โญ 612 Python ๐Ÿ‘ค BurhanUlTayyab User ๐Ÿ• Updated 2026-05-04 ๐Ÿ“… Created 2023-01-24
29
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)

voidful
โญ 564 Python ๐Ÿ‘ค voidful User ๐Ÿ• Updated 2026-04-23 ๐Ÿ“… Created 2021-03-18
30
codota/tabnine-intellij

Jetbrains IDEs client for TabNine. Compatible with all IntelliJ-based IDEs. https://plugins.jetbrains.com/plugin/12798-tabnine

codota
โญ 541 Kotlin ๐Ÿ‘ค codota Organization ๐Ÿ• Updated 2024-03-24 ๐Ÿ“… Created 2019-07-27

Frequently Asked Questions

1

What is the most popular #gpt-2 repository on GitHub?

The top ranked open source #gpt-2 project on GitHub is BlinkDL/RWKV-LM with 14,786 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.

2

Which programming languages are most used in #gpt-2 repositories?

Among the top ranked #gpt-2 projects on GitHub, the most common programming languages are Python, Jupyter Notebook, TypeScript, Shell.

3

How is the #gpt-2 repository ranking calculated?

We track 30 active open source repositories tagged with #gpt-2 (500+ stars), totaling 111,632 stars with an average of 3,721 stars per repository. Rankings update daily from the GitHub API.