MMihai_LeanZeroinleanzero.hashnode.dev·1d ago · 67 min readClaude Sonnet 5.5 vs Opus 5.5 vs GPT-6.1 SolClaude Sonnet 5.5 edged Claude Opus 5.5 on our general-programming benchmark, a payments app, 0.7984 to 0.7926, a margin I read as level. It built the better app, though: it earned 0.9894 to Opus's 0.00
ARAleksei Romanovingfactor.hashnode.dev·Sep 26 · 10 min readLoRA & DoRA: The Math, Memory, and Trade-offsEvery engineer who has ever tried to fine-tune a modern 27B or 70B parameter model knows the rude awakening of GPU memory arithmetic. You look at the raw model weights and think: “27 billion parameter00
FMFotie M. Constantinblog.fotiecodes.com·Sep 23 · 3 min readProject Turaco Is Finally Showing PromiseFor more than a year, I have been trying to answer one question: can we build a machine translation model that translates English into natural Cameroon Pidgin without sounding like it is guessing? Tha01B
THTaha husseinintahahussein.hashnode.dev·Sep 18 · 7 min readFine-Tuning an LLM: What Actually Happens Under the Hood?Fine-Tuning an LLM: What Actually Happens Under the Hood? You have probably heard phrases like: "Fine-tune the model." "Use LoRA." "Train the LLM on your own data." "Use PEFT." But what do these ter00
RSRahul Sai Indeevar Vinrahul-ai.hashnode.dev·Sep 16 · 10 min readParameter-Efficient Fine-Tuning: From LoRA to QLoRAFine-tuning Large Language Models (LLMs) used to be an option only for organizations with massive compute budgets. Full fine-tuning requires updating and storing every parameter, gradient, and optimiz20
RSRahul Sai Indeevar Vinrahul-ai.hashnode.dev·Sep 8 · 14 min readLLM Post-Training: From Full Fine-Tuning to PEFT, Adapters, and Soft PromptsLarge Language Models (LLMs) arrive with immense foundational knowledge acquired during pre-training. However, deploying them to specialized real-world domains—such as legal document parsing, medical 10
PRPRANJUL RATHOURinpranjulrathour.hashnode.dev·Sep 5 · 9 min readA GenAI engineer's field guide for college students: RAG, fine-tuning, hackathons and shippingI'm Pranjul Rathour, a GenAI engineer from Kanpur. Over the last two years I have built five production AI systems, won three student hackathons and lost one that mattered more, and mentored 200+ stud00
RSRahul Sai Indeevar Vinrahul-ai.hashnode.dev·Aug 28 · 9 min readUnderstanding LoRA: Parameter-Efficient Fine-Tuning for Modern LLMsLarge Language Models (LLMs) and foundation models like LLaMA, GPT, and ViTs have billions of parameters. As these models scale, traditional full fine-tuning—updating every weight in the network—becom10
SPSandeep Pandainhashnode.com·Jul 24 · 9 min readHow to Fine-Tune an Open-Weights LLM: A Hands-On Guide Using Inklingtldr: Fine-tuning an LLM means continuing to train an existing model on your own data so it specializes in your task. With an open-weights model like Thinking Machines' Inkling (975B parameters, 41B a10
LWLearn with HJinhardeepjethwani.hashnode.dev·Jul 11 · 6 min readFine-Tuning vs RAG: Which One Should You Actually Use?🚀 Fine-Tuning vs RAG: Which One Should You Actually Use? 👋 Welcome to Day 10 of 90 Days of AI. 🎯 Today we are tackling Fine-Tuning vs RAG: Which One Should You Actually Use?. The mission is simple00
