Sign in

Compare repositories

This page shows the Star History and the facts of 2 to 5 repositories in the Repository Index, side by side. You choose the repositories. The page does not rank them.

Stars gained: From Apr 26, 2026 to Nov 4, 2026, each from zeroStars gainedFrom Apr 26, 2026 to Nov 4, 2026, each from zero0200400Apr 26Nov 4, 2026BlinkDL/RWKV-LMmicrosoft/LoRA
Stars: The star count at the end of each dayStarsThe star count at the end of each day14KApr 26Nov 4, 2026BlinkDL/RWKV-LMmicrosoft/LoRA

Facts

FactBlinkDL/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.

microsoft/LoRA

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

Stars14,77213,903
Net stars, last 30 days+41+84
Largest star day+8 on Jun 30, 2026+10 on Jun 1, 2026
Milestone reached in the recordNoneNone
Forks1,026936
LanguagePythonPython
LicenseAPACHE-2.0MIT
CreatedAug 8, 2021Jun 18, 2021
Last pushNov 4, 2026Dec 17, 2024
ArchivedNoNo
Health facts: Maintenance4 of 4 checks1 of 4 checks
Health facts: Releases0 of 3 checks0 of 3 checks
Health facts: Security practice0 of 1 check1 of 1 check
Health facts: Community files1 of 3 checks2 of 3 checks
Commits, last 13 weeks120
Weeks with commits, last 5232 of 520 of 52
In the Repository Index sinceOct 22, 2026Oct 22, 2026

Topics that all of them have on the Repository Host: deep-learning, gpt-2, gpt-3, language-model, pytorch. The facts come from the Repository Host and from the Star History that AwesomeRepos records. A shared topic does not mean that one repository can replace another. Each Health Facts row is one dimension alone. AwesomeRepos does not add them into one score. How each check is defined

Example: oven-sh/bun, denoland/deno, nodejs/node