train-llm-from-scratch
train-llm-from-scratch is A straightforward method for training your LLM, from downloading data to generating text. - FareedKhan-dev/train-llm-from-scratch. It is ranked #775 on the Dev Radar, in AI dev tools, first seen 45 days ago and shared in 4 posts (31.7k views).
GitHub - FareedKhan-dev/train-llm-from-scratch: A straightforward method for training your LLM, from downloading data to generating text. · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation train-llm-from-scratch Public Notifications You must be signed in to change notification settings Fork 1.8k ( 1.8k ) Star 13.1k ( 13.1k )…
What people said about train-llm-from-scratch on X
This 12.5K-star GitHub repo is basically an entire LLM engineering course hiding inside one codebase. It starts with raw text and builds a Transformer in plain PyTorch, then keeps going through pretraining, supervised fine-tuning, reward modeling, preference optimization and reinforcement learning. The repository…
— @techNmak, 7 days ago · 659 likes · see the post
嘴上天天喊搞AI，真问Transformer是啥，能讲利索的没几个。 有个仓库够狠，零基础手搓一个GPT，高级库一概不碰。Attention、多头、前馈、Embedding、残差、Layer Norm怎么拼起来，全摊开给你看。而且不只模型，整条链子都在： 1️⃣ 数据下载、预处理、训练、生成一条龙走完 2️⃣ 训练数据用The Pile，22个来源825GB 3️⃣ tiktoken分词，存进HDF5 4️⃣ 预训练完还附上SFT和RLHF的路数 改几个配置就能调大小。13M参数上下就开始拼对语法和单词，白蹭Colab或Kaggle的T4，练一天就出货。…
— @bkdgiffug, 12 days ago · 174 likes · see the post
Alternatives to train-llm-from-scratch
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- dsh-superagent-prototype — DeepSeek open-sourced the design behind its always-on 'Super-agent': no chat window, and reportedly nearly half the…
- Agents in flight — Give it a try
- strata — and more
- project-maya — Plus a round of fixes, UI improvements and community PRs.
train-llm-from-scratch in numbers
- Rank on the Dev Radar: #775 of 9191
- Shared in 4 posts by 4 accounts: @techNmak, @bkdgiffug
- 31.7k views on those posts
- First seen 45 days ago, last shared 7 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI dev tools
FAQ
What is train-llm-from-scratch?
A straightforward method for training your LLM, from downloading data to generating text. - FareedKhan-dev/train-llm-from-scratch It was first shared on X 45 days ago and is ranked #775 on the Dev Radar.
Is train-llm-from-scratch free?
It is open source.
Who shared train-llm-from-scratch?
4 accounts on X, including @techNmak, @bkdgiffug, in 4 posts totalling 31.7k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 21:07 UTC. Full method.