Learn
Practical guides to fine-tuning, distillation, and deploying small language models.
Is Fine-Tuning Worth It? When to Fine-Tune vs Prompt
Prompt engineering is fast and flexible, but fine-tuning delivers higher accuracy, lower latency, and lower cost at scale. Learn when each approach makes sense and how to decide.
Model Distillation Tutorial: From LLM to Deployable SLM
A hands-on tutorial for distilling a large language model into a small, deployable student model. Covers the full pipeline from teacher selection to production deployment.
No-Code Model Fine-Tuning: Train a Custom SLM Without Writing Code
Learn how to fine-tune a small language model without any coding. Discover no-code and low-code platforms that let you create custom NLP models using just a prompt and a few examples.
Air-Gapped and On-Premise LLM Deployment
Running a language model inside a network with no outbound internet access — why frontier APIs are structurally unavailable there, why a distilled small model fits the hardware that already exists, and what a working deployment contains.
Do You Need to Fine-Tune the Tokenizer?
Almost never — the tokenizer that shipped with a checkpoint is bound to its embedding matrix, and changing the vocabulary throws away pretrained representations you cannot cheaply relearn.
Does the Student Need the Same Architecture as the Teacher?
No — text-level distillation transfers behaviour through generated examples, so student and teacher can come from unrelated model families. When architecture does start to matter.
Full Fine-Tuning vs Adapters
Full fine-tuning rewrites every weight; adapters leave the base frozen and train a small add-on. Here is what counts as an adapter and where the two approaches genuinely diverge.
FunctionGemma 270M for Multi-Turn Tool Calling
Google's FunctionGemma scores 9.9-38.8% on multi-turn tool calling before training and 90.9-96.7% after, and the gap between those two numbers is the whole story of using a 270M function caller.
Gemma 3 270M: What It Can Do
The capability envelope of Google's 270M-parameter Gemma 3 — which tasks it clears after fine-tuning, which it cannot reach at any training budget, and why its benchmark variance is so wide.