Yogendra Pratap Singh (Tech Architect)·Oct 31Part 17 — Llama: Understanding Meta’s Open-Weight AI ModelsWhat Llama is, how it differs from other AI models, and how developers can build AI-powered applications with greater control over…
Nerio Scale·Oct 19China Is Giving AI Away for Free. Meta Couldn’t Keep UpLlama. That’s the name Meta gave the artificial intelligence it decided to give away. Not rent, not sell. Give away. Anyone on Earth could…
Jupiter Smith·Sep 23How to Fine-Tune Qwen or Llama for Domain-Specific Code GenerationA working guide to dataset curation, LoRA training, and shipping a quantized model you can run on your own machine.
Adrian Angel Sanz Melchor·Sep 17Fitting Qwen3.8–27B on 16 GB of VRAM with 128K context at usable speedsBeellama + Community quantizations making wonders on humble setups.
Ahmadmujtaba·Sep 10Fine-Tuning LLaMA for a Content App: What LoRA and PEFT Actually Bought UsWhen I joined Recce as a Machine Learning Engineer, the brief was simple to say and hard to do: help people cut through content overload…
Hillary Beth Trivette·Aug 1The difference between an alpaca and a llamaAlpaca vs. Llama: What’s the Difference?
Aravind·Aug 1Llama.cpp vs vLLM vs Ollama: Choosing the Right Local LLM EngineRunning Large Language Models (LLMs) locally has never been easier. Whether you’re experimenting on a laptop, building a private AI…
Vaishnavkathiran·Jul 14Building an AI Data Analyst with Llama: From Raw Data to Business InsightsHow I built an AI-powered data analyst that understands datasets, performs analysis, and generates insights using open-source LLMs.
