[HN Gopher] Show HN: Create-LLM - Train your own LLM in 60 seconds
___________________________________________________________________
Show HN: Create-LLM - Train your own LLM in 60 seconds
https://medium.com/@theaniketgiri/three-months-ago-i-wanted-...
Author : theaniketgiri
Score : 36 points
Date : 2025-10-26 09:53 UTC (13 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| kk58 wrote:
| Does this work on mac
| theaniketgiri wrote:
| Yep, works fine on Mac. Try the nano or tiny templates if you
| want quicker training runs
| efilife wrote:
| 2 questions: how much of this project is AI generated and how
| much of only the readme is AI generated?
| theaniketgiri wrote:
| Mostly the repetitive stuff like README generation and pushing
| code with meaningful commit messages was handled by AI. The
| actual work and logic were done by me.
| joshribakoff wrote:
| What about the commit that added tens of thousands of lines
| of markdown claiming to be an AI summary?
|
| Or the meaningful commit message of "."
|
| And the commit editing 1,000s of lines of python code
| mislabeled as a docs change?
| theaniketgiri wrote:
| Totally fair question!
|
| Docs / Markdown: AI handled repetitive stuff like READMEs
| and summaries.
|
| Core logic / Python: fully written by me.
|
| Commit messages: some minimal ones just for quick
| iterations -- the real work is in the code.
|
| AI helped with boilerplate so I could ship faster; all
| functionality is hand-crafted.
| joshribakoff wrote:
| If the AI did the boilerplate that implies it was not
| fully written by you.
|
| The "meaningful commit messages" -- again are a single
| period as the message for a single commit for the entire
| python portion of the codebase.
|
| My question was rhetorical. Whether the AI did it or a
| human did, it burns credibility to refer to things that
| don't exist (like "meaningful commit messages")
| teruakohatu wrote:
| Hacker News is a better place when we don't attack people
| sharing their work. Your point was made.
|
| Well done to the author for shipping code. I look forward
| to trying it out.
| darepublic wrote:
| I don't quite understand how you get from this:
|
| > I wanted to understand how these things work by building one
| myself.
|
| Directly to this:
|
| What if training an LLM was as easy as npx create-next-app?
|
| I mean that the second thought seems to be the opposite of the
| first (what if the entirety of training llm was abstracted behind
| a simple command)
| theaniketgiri wrote:
| Great question - I should've been clearer.
|
| When I started, I wanted to understand LLMs deeply. But I hit a
| wall: tutorials were either "hello world" toys or "here's 500
| lines of setup before you start."
|
| What I needed was: "give me working code quickly, THEN let me
| modify and learn."
|
| That's what create-llm does. It scaffolds the boilerplate (like
| create-next-app), so you can spend time learning the
| interesting parts: - Why does vocab size matter? (adjust
| config, see results) - What causes overfitting? (train on small
| data, see it happen) - How do different architectures perform?
| (swap templates, compare)
|
| It's "easy to start, deep to master." The abstraction gets you
| running in 60 seconds, then you dig into the code
| seg_lol wrote:
| The blogpost is some of the best LLM greentext I have seen for
| targeting the hn hivemind. Everything about this is :chefs kiss:
___________________________________________________________________
(page generated 2025-10-26 23:01 UTC)