Machine Learninggeneral
[Part 3-Final] I Distilled DeepSeek Reasoning Into My 360M Model, Then Trained It Again With RL
The long run study of the LLM has now ended
…
Loading
Please wait a moment.
Please wait a moment.
Reverse-engineering notes ordered by publication date. Choose a category to narrow the list.
The long run study of the LLM has now ended
Deepseek Style for Tiny LLM
Played with a small language model locally.
Not related to reverse engineering :) and a bit too academic
Reverse Engineering iOS.
Just playing my old favourite games ~~~
Just some notes from my holiday, when I started playing with IDA Pro again.