Unboxing LLMs > loading...

Author: Rakshit Kalra

Home / Archives

Latest Posts
April 1, 2025
Teaching Llama New Tricks: Memory-Efficient Trainable Tokens with LoRA
March 18, 2025
If Your Code Were Alive: From Construction to Cultivation
March 13, 2025
Aggressive Quantization: How Low Can You Go?
March 10, 2025
Four Habits of Highly Effective STaRs: Reviewing “Cognitive Behaviors that Enable Self‑Improving Reasoners”
March 3, 2025
Native Sparse Attention: Making Long‑Context Transformers Truly Practical
February 25, 2025
Structure Over Substance: A Deep Dive into “LLMs Can Easily Learn to Reason from Demonstrations”
1 2 3 4 5 6 … 22