Fine tuning and training
Adapt a model to your task with good data and careful training runs.
12tutors
2teachers
1free to start
$5 to $14per paid lesson
Fine tuning and training tutors
12 tutors
Instruction tuning a base model
Instruction tuning a base model
Turn a base model that only continues text into one that follows instructions in a reliable format75 lessonsSampleNeha Varadan$9LoRA and parameter efficient fine tuningLoRA and parameter efficient fine tuning
Fine tune large models on modest hardware by training small low rank adapters instead of every weight66 lessonsSampleNeha Varadan$9Evaluating a model after fine tuningEvaluating a model after fine tuning
Prove a tuned model is actually better, on your task and everywhere else it matters65 lessonsSampleNeha Varadan$8Planning the cost of a training runPlanning the cost of a training run
Estimate compute, time, memory and budget for a training or fine tuning run before you spend65 lessonsSampleMagnus Eriksen$7Your first fine tune, start to finishYour first fine tune, start to finish
Run one small, honest fine tuning project end to end and decide whether it was worth doing64 lessonsSampleNeha Varadan$6Preference tuning: RLHF, DPO and related methodsPreference tuning: RLHF, DPO and related methods
Understand how models are tuned on human preferences, from reward models to direct preference losses60 lessonsSampleNeha Varadan$14Fine tune, prompt or retrieve?Fine tune, prompt or retrieve?
Choose between prompting, retrieval and fine tuning for your problem, and know why59 lessonsSampleNeha VaradanFreeQuantisation: smaller, faster modelsQuantisation: smaller, faster models
Shrink models with lower precision numbers and measure exactly what quality you trade away49 lessonsSampleMagnus Eriksen$9Preparing a fine tuning datasetPreparing a fine tuning dataset
Build a clean, consistent, legally sound dataset that teaches a model exactly what you intend39 lessonsSampleNeha Varadan$5Synthetic data for training, used with careSynthetic data for training, used with care
Generate training data with models where it helps, and filter, verify and document it properlyNeha Varadan$7Catastrophic forgetting and how to limit itCatastrophic forgetting and how to limit it
Measure what a model loses when you fine tune it, and use replay, regularisation and merging to limit itNeha Varadan$12Knowledge distillation: teaching a smaller modelKnowledge distillation: teaching a smaller model
Train compact student models from large teachers with soft targets, generated data and careful evaluationMagnus Eriksen$12Teachers who teach Fine tuning and training
They wrote the lesson plans these tutors follow.
Neha Varadan
Fine tuning with judgment: when to do it, how to do it well, and how to know it workedfine tuning strategy, dataset preparation, LoRA and parameter efficient methods9 tutorsSampleMagnus Eriksen
Making models fast, small and affordable: hardware, quantisation, serving and edgeGPUs and accelerators, training cost estimation, quantisation9 tutorsSampleMore in Machine learning
- Machine learning How models learn from data: training, validation, overfitting and the classic methods. 35 tutors
- Data science and statistics Clean data, explore it and draw conclusions you can defend. 30 tutors
- Math for AI The linear algebra, calculus and probability behind modern models, one idea at a time. 23 tutors
- Deep learning Neural networks from single neurons to full training loops, with worked examples. 28 tutors
- NLP Work with text: tokens, embeddings, classification, translation and speech. 14 tutors
- Computer vision Models that see: classification, detection, segmentation and their limits. 14 tutors
- MLOps and deployment Ship models to production and keep them healthy: serving, monitoring, updates. 18 tutors