Amit Yadav

1. Why TinyLlama? “Sometimes, smaller isn’t just faster — it’s smarter.” I’ve fine-tuned a bunch of models over the past few months — Mistral, Phi, even the newer LLaMA variants. But when I stumbled upon TinyLlama, it hit a sweet spot I didn’t expect. If you’re working with constrained resources — say, a single A100 … Read more

1. Why I Fine-Tuned Gemini Instead of Using It Out-of-the-Box “A model that knows everything—until it needs to know your everything.” That pretty much sums up my experience with base Gemini. When I first got access to Gemini Pro via Google Cloud, I was genuinely impressed by the zero-shot reasoning. It was fast, fluent, and … Read more

1. Intro: Why I Still Fine-Tune GPT-3 in 2025 “Just because you’ve got a spaceship doesn’t mean you stop using the plane.” It’s 2025. GPT-4-Turbo is running laps, and everyone’s building apps on top of APIs. But me? I’m still fine-tuning GPT-3 — and not out of nostalgia. I’ve personally worked on projects where GPT-3, … Read more

1. Quick Context: Why Fine-Tune GPT-2 in 2025? “Just because you have a hammer, doesn’t mean everything needs to be a nail.”That’s how I see the GPT-4 hype sometimes. Yes, GPT-4 is powerful. Yes, it’s everywhere. But here’s the deal: not every project needs a 100B+ parameter monster chewing through tokens on rented A100s. I … Read more

1. Why Fine-Tune LLaMA 3 Instead of Just Prompting? “Give a man a prompt and you solve one task. Teach a model through fine-tuning, and you automate that task forever.” I’ve worked with LLMs long enough to know that prompting can only take you so far. I remember this specific internal project where we were … Read more

1. Why Fine-Tune LLaMA 2 Instead of Using It Out-of-the-Box? “You don’t need a scalpel to slice bread — unless the bread is custom-made and laced with data-specific requirements.” That’s pretty much how I explain fine-tuning to other folks on my team. Here’s the deal: I’ve worked on projects where prompt engineering just couldn’t cut … Read more

1. Intro: Why Fine-Tune LLaMA Instead of Starting from Scratch? “Give me a GPU and a foundation model, and I’ll show you results that a scratch-built model could only dream of.” When I first started working with LLaMA, I wasn’t aiming to reinvent anything. I just needed a model that could adapt quickly to my … Read more

1. Prerequisites (But Only the Non-Obvious Stuff) When I first got Alpaca up and running, the biggest roadblocks weren’t the ones you’d expect. It wasn’t about “how to install PyTorch”—it was the stuff that hits you after everything looks set up. GPU Requirements: Don’t Assume It’s Enough I trained Alpaca (7B) with LoRA on a … Read more

1. Why Fine-Tune PaLM (Bard)? “A well-crafted prompt is a patch; fine-tuning is a firmware upgrade.” I’ve used Bard (backed by PaLM) across a few client-facing NLP use cases — summarization, domain-specific Q&A, and even multi-turn chat systems. And here’s what I’ve found: prompt engineering hits a ceiling pretty fast once your use case goes … Read more

1. Introduction “Open models won’t replace closed ones overnight — but they will quietly take over the corners that matter most.” When I first got my hands on Dolly v2, I wasn’t expecting much. Another open-source LLM in a sea of many, right? But after some deep dives and fine-tuning experiments, I realized Dolly is … Read more