-
Training the Tokenizer
📅 03 Jun 2025 -
Self-Attention in Transformers
📅 21 Jun 2025
↳ Masked Self-Attention
📅 25 Jun 2025 -
KV (Key-Value) Cache in Transformers
📅 26 Jul 2025 · Reducing inference latency using KV cache
- How Does Temperature Change LLM Responses?
📅 09 Jul 2025 · Effect of temperature on next-token probability distribution
- Building MakeMyDocsBot
📅 20 Dec 2025 · Automated multi-language documentation sync across feature branches
- RLM Interactive Console (Live Demo)
📅 21 Jan 2026 · Interactive REPL-style environment for exploring Retrieval + LLM reasoning pipelines
↳ Source Code: RLM Demo Repository
FastAPI backend + Next.js frontend · Deployed on Hugging Face Spaces
- MoE Routing Calculation (Excel Walkthrough)
📅 25 Jan 2026 · Step-by-step Excel breakdown of router logits → top-k selection → normalized expert probabilities
Includes: top-k masking, -∞ replacement, softmax, and final expert routing weights

