LLM

5 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
Using LLMs and Cursor to become a finisher
LLM

Using LLMs and Cursor to become a finisher

Struggling to finish side projects due to limited time? In my latest blog post, I share how I improved my productivity using AI tools like LLMs and Cursor IDE. Learn to refine specs, bootstrap code, and iterate effectively to rapidly build and deploy your projects—even with a busy schedule.
Zohaib Rauf
8 min read
Run custom GGUF model on Ollama
ollama

Run custom GGUF model on Ollama

Learn how to install a custom Hugging Face GGUF model using Ollama, enabling you to try out the latest LLM models locally. This guide covers downloading the model, creating a Modelfile, and setting up the model in Ollama and Open-WebUI.
Zohaib Rauf
2 min read
LLM

Guide to extending OpenWebUI using Pipelines

Explore OpenWebUI's Pipelines: extend your self-hosted LLM interface. Learn to create custom pipelines, from filters to tools. Intercept LLM interactions, implement function-calling, and integrate new providers. Enhance AI workflows or build RAG systems with this guide to OpenWebUI's extensibility.
Zohaib Rauf
7 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