[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![_avichawla Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1175166450832687104.png) Avi Chawla [@_avichawla](/creator/twitter/_avichawla) on x 41.6K followers
Created: 2025-07-21 06:40:13 UTC

Those were the X stages of training an LLM from scratch.

- Start with a randomly initialized model.
- Pre-train it on large-scale corpora.
- Use instruction fine-tuning to make it follow commands.
- Use preference & reasoning fine-tuning to sharpen responses.

Check this 👇

![](https://pbs.twimg.com/tweet_video_thumb/GwXKRlwa4AAllmM.jpg)

XXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947184824760029316/c:line.svg)

**Related Topics**
[llm](/topic/llm)
[$avijo](/topic/$avijo)

[Post Link](https://x.com/_avichawla/status/1947184824760029316)