Learn
Practical guides to fine-tuning, distillation, and deploying small language models.
What Is Quantization?
Quantization stores model weights at lower numerical precision so the same architecture occupies less memory and streams faster: how the block-scale mechanism works, what each bit width costs, and where the damage shows up first.
What Is Question Answering as a Training Task?
The question-answering task type trains a model to return a targeted answer rather than a summary: what distinguishes it from the two QA variants, what the job description must specify, and how the answers get scored.
What Is Teacher Evaluation?
Teacher evaluation scores the teacher model on your held-out test set before any training runs, a feasibility gate that tells you whether the task is solvable and what accuracy the student should be aiming at.
What Is Text Classification with a Small Language Model?
Text classification trains a small model to emit exactly one label from a fixed set: how the task works on distil labs, what the training files contain, and the measured lift fine-tuning gives over a base model.
What Is Tool Calling and How Do You Train for It?
Tool calling turns a natural-language request into one schema-valid function call. What the task type expects in your files, which models are eligible, and the measured jump fine-tuning produces on sub-1B students.
What Makes a Good Production Trace?
What the trace processing pipeline scores a conversation on (relevance, coherence, and repairability), and why a trace can be a poor training label yet still be excellent seed data.
Why Every Path to Training Data Ends in Synthetic Data
However you supply seed data (live traffic, uploaded traces, or a hand-written set), the platform converts it into synthetic training data before any fine-tuning happens. Here's why.
Why METEOR and BLEU Are Legacy Metrics
METEOR has been retired from the distil labs scorecard and BLEU was never on it. Here's what the platform reports instead, and why a whole class of word-overlap metrics misleads on generation tasks.
Knowledge Distillation Explained: Teacher-Student Training for LLMs
Learn how knowledge distillation works: the teacher-student training process that compresses large language models into small, fast, deployable models without losing accuracy.