Learn
Practical guides to fine-tuning, distillation, and deploying small language models.
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.
Can You Combine RAG and Fine-Tuning?
Yes. You fine-tune the generator to answer strictly from retrieved passages, including deliberately irrelevant ones. What the training data looks like and where the combination breaks.
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 can't 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 can't reach at any training budget, and why its benchmark variance is so wide.