AAKSHAYinakshayetukurihashnodedev.hashnode.dev·Jul 4 · 4 min readFine-Tuning BERT to Classify Security Logs — And the 100% Accuracy Trap I Fell IntoThe idea Security teams deal with a constant stream of raw log lines — logins, file access, network connections, the occasional actual attack. Most of that triage still runs on hand-written regex rule00
RRishikantinrishiii2.hashnode.dev·Jun 28 · 7 min readThe Architecture That Changed the World: Transformers, BERT, and the LLM RevolutionIn our previous post, we discovered that Recurrent Neural Networks (RNNs) and LSTMs suffer from a massive flaw: they must process data sequentially, one word at a time. This makes them agonizingly slo00
TVTanmaiyee Vadlooriinnvidia-nim.hashnode.dev·Jun 11 · 19 min readBuilding a Production-Grade Manufacturing Defect Analyzer with NVIDIA NIM — Zero GPU RequiredTags: NVIDIA NIM · LLM Integration · Streamlit · Manufacturing AI · Python · Prompt Engineering · AWS · Production Architecture Why I Built This India has over 300,000 registered manufacturing units.00
RPRavi Panchalincodeandmodels.hashnode.dev·May 29 · 13 min readBharatGen's FinanceParam (Quantized): 5 Real Drawbacks We Found After Using It👨💻 Authors Ravi Panchal · Arup Das · Anurag Jaiswal B.Tech 3rd Year, AI & Data Science Gati Shakti Vishwavidyalaya (GSV), Vadodara 📧 Contact: ravi.panchal.kaithi@gmail.com The Hype Was Real. S00
HAHarsh Agaleinharshagale.hashnode.dev·May 22 · 5 min readHow I Fine-Tuned Llama 2 Using QLoRA on Free GPU ResourcesTraining and fine-tuning Large Language Models (LLMs) is often considered expensive and hardware-intensive. Most tutorials online assume access to powerful GPUs with large amounts of VRAM, which can b00
JJebitokinsharonjebitok.com·May 9 · 21 min readUnderstanding AI Supply Chains (TryHackMe)TryHackMe Room: Understanding AI Supply Chains Introduction Every time you use Claude, ChatGPT, GitHub Copilot, or any AI-powered product, you are trusting a model trained somewhere, on some data, by 00
NKNitish kumarinhackathon-nitish.hashnode.dev·Apr 26 · 5 min readThe Day I Realized AI Could Ship Code Faster Than We Could Secure ItBuilt in the open. Trained in public. Shipped with the spirit of the open-source AI community. A February Evening That Changed My Thinking On 17 February, I walked into an Anthropic event carrying o00
AAAbstract Algorithmsinabstractalgorithms.hashnode.dev·Apr 18 · 30 min readFine-Tuning LLMs: The Complete Engineer's Guide to SFT, LoRA, and RLHFTLDR: A pretrained LLM is a generalist. Fine-tuning makes it a specialist. Supervised Fine-Tuning (SFT) teaches it your domain's language through labeled examples. LoRA does the same with 99% fewer tr10
DKDeepak Kumarindebugdeploygrow.hashnode.dev·Apr 3 · 4 min read🚀 How I Built a RAG AI Assistant with LangChain & Llama 3Introduction Hey everyone! 👋 I’m currently working as an AI-Augmented Cloud Platform Architect, focused on designing scalable systems that integrate LLMs, cloud infrastructure, and real-world data. R00
AKAdam Kinginflexai.hashnode.dev·Mar 31 · 6 min readFlexBench: An Open-Source, Modular MLPerf Benchmark for LLM InferenceTL;DR AI system benchmarks like MLPerf struggle to keep pace with the rapidly evolving model landscape, making it difficult for organizations to make informed deployment decisions. We believe benchmar00
