reasoning-from-scratch
reasoning-from-scratch is Implement a reasoning LLM in PyTorch from scratch, step by step - rasbt/reasoning-from-scratch. It is ranked #3005 on the AI Radar, in AI research, first seen 12 days ago and shared in 3 posts (2.2k views).
GitHub - rasbt/reasoning-from-scratch: Implement a reasoning LLM in PyTorch from scratch, step by step · GitHub Skip to content Navigation Menu Sign in Appearance settings 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 reasoning-from-scratch Public Notifications You must be signed in to change notification settings Fork 880 ( 880 ) Star 5.5k ( 5.5k ) You must be signed…
What people said about reasoning-from-scratch on X
Now anyone can build their own reasoning model. Sebastian Raschka just released a completely free course, with all the code open source. Using a small Qwen3-0.6B model, you can learn how reasoning models are actually trained. You'll learn how to: • Get a model to try different ways to solve a problem • Automatically…
— @hqmank, 12 days ago · 26 likes · see the post
Almost anyone can now build their own reasoning model. Sebastian Raschka released a completely free, open-source course using Qwen3-0.6B to show how reasoning models are trained, from reward-based learning and GRPO to reward hacking. You’ll run the code yourself and watch the model evolve, then train a smaller model…
— @davidarngar, 10 days ago · 1 likes · see the post
Sebastian Raschka released a completely free, open-source course on building reasoning models from scratch, using Qwen3-0.6B as a hands-on example. Learn how to train models to explore multiple solutions, verify answers, improve reasoning with reward-based training and GRPO, and even game their reward systems. The…
— @davidarngar, 10 days ago · 1 likes · see the post
Alternatives to reasoning-from-scratch
- academy.dair.ai — Chat with Paper
- alphaXiv — Now on @askalphaxiv
- flashprove — Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that…
- moe-blogpost — A hands-on guide to training Mixture-of-Experts models
- liberai.com — Technical blog
- Science's Last Exam — Can AI do research, end to end? Science's Last Exam defines and measures whether an AI agent can carry a research goal…
reasoning-from-scratch in numbers
- Rank on the AI Radar: #3005 of 10402
- Shared in 3 posts by 2 accounts: @hqmank, @davidarngar
- 2.2k views on those posts
- First seen 12 days ago, last shared 10 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI research
FAQ
What is reasoning-from-scratch?
Implement a reasoning LLM in PyTorch from scratch, step by step - rasbt/reasoning-from-scratch It was first shared on X 12 days ago and is ranked #3005 on the AI Radar.
Is reasoning-from-scratch free?
It is open source.
Who shared reasoning-from-scratch?
2 accounts on X, including @hqmank, @davidarngar, in 3 posts totalling 2.2k 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. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.