LLM-Training

2 posts
DeepSeek-R1: A Peek Under the Hood
LLM-Training

DeepSeek-R1: A Peek Under the Hood

DeepSeek-R1 uses cost-effective Reinforcement Learning to unlock emergent reasoning. By rewarding correct, verifiable steps, it refines logic and answers—showcasing how systematic feedback can reduce data needs and boost performance. Here I discuss my understanding from research paper.
Zohaib Rauf
6 min read
how-to

A beginners guide to fine tuning LLM using LoRA

Discover how to create a synthetic dataset, select the right metrics for evaluation, and fine-tune your model using LoRA for a narrow scenario. Plus, learn how to serve your model efficiently using LLaMa.cpp on Mac/Linux.
Zohaib Rauf
8 min read