🌍 Live Open Source Explorer

Explore live open-source projects and AI models.

Search public open-source repositories from GitHub and AI models from Hugging Face. Every page shows 10 results with clean pagination.

Curated Tools → Curated AI Models 🤖 Submit Tool ＋

Live sources

🐙

GitHub

Open repos

🤗

Hugging Face

AI models

🐳

Self Hosted

GitHub search

🧠

LLM

Model search

🔎 Live Search

Search live open-source data

Search GitHub repositories and Hugging Face models directly, then explore stars, downloads, source links and project details.

Reset Search ↻

Search keyword

🔎

Source

🌐

Try keywords like automation, CRM, analytics, chatbot, llama or workflow.

Choose where to search live data.

CRM Workflow Chatbot Llama

Live Results

GitHub Open Source Repositories

Search: train-llm-from-scratch

Page 1

Showing 10 results from 12

jingyaogong/minimind

GitHub Python Apache License 2.0

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

★ 51,129 Forks 6,561 jingyaogong Updated 04 Jun 2026

External source

GitHub

View Details → Open Source ↗

FareedKhan-dev/train-llm-from-scratch

GitHub Python MIT License

A straightforward method for training your LLM, from downloading data to generating text.

★ 4,239 Forks 580 FareedKhan-dev Updated 04 Jun 2026

External source

GitHub

View Details → Open Source ↗

zhanshijinwat/Steel-LLM

GitHub Jupyter Notebook

Train a 1B LLM with 1T tokens from scratch by personal

★ 806 Forks 79 zhanshijinwat Updated 02 Jun 2026

External source

GitHub

View Details → Open Source ↗

wei-potato/Train-llm-from-scratch

GitHub Python

使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力

★ 166 Forks 21 wei-potato Updated 04 Jun 2026

External source

GitHub

View Details → Open Source ↗

marimo-team/modernaicourse

GitHub Python Apache License 2.0

A companion to CMU professor Zico Kolter's Intro to Modern AI. Learn the basics of machine learning, then train your own LLM from scratch.

★ 107 Forks 7 marimo-team Updated 02 Jun 2026

External source

GitHub

View Details → Open Source ↗

KastanDay/video-pretrained-transformer

GitHub Jupyter Notebook MIT License

Multi-model video-to-text by combining embeddings from Flan-T5 + CLIP + Whisper + SceneGraph. The 'backbone LLM' is pre-trained from scratch on YouTube (YT-1B dataset).

★ 54 Forks 11 KastanDay Updated 13 Feb 2026

External source

GitHub

View Details → Open Source ↗

timmzimm/Train-LLM-from-scratch

GitHub Python

No description available from source.

★ 22 Forks 1 timmzimm Updated 09 Jan 2025

External source

GitHub

View Details → Open Source ↗

131AIClub/SimpleLLM

GitHub Python MIT License

Implement and train a Tiny LLM from scratch!

★ 20 Forks 1 131AIClub Updated 15 Mar 2026

External source

GitHub

View Details → Open Source ↗

vvr-rao/Training-a-Mini-114M-Parameter-Llama-3-like-Model-from-Scratch

GitHub Python

Trained a 114 million Parameter LLM from Scratch.

★ 19 Forks 4 vvr-rao Updated 05 Sep 2025

External source

GitHub

View Details → Open Source ↗

LF-Luis/MyLLM

GitHub Python GNU General Public License v3.0

Personal project to learn how to build and pre-train a modern LLM from scratch.

★ 16 Forks 0 LF-Luis Updated 07 Dec 2025

External source

GitHub

View Details → Open Source ↗

Pagination Page 1 of 2

10 results on this page · 12 total found

Showing first 12 accessible GitHub results.