AI Automation
Courses
6 course options · Compare the learning

LLM Training, Fine-Tuning and Post-Training Courses

Compare curricula by model lifecycle stage: architecture, pretraining, supervised/preference post-training, RL fine-tuning and evaluation.

Illustrative workflow

A concrete way to compare the learning

Text/data → architecture or training stage → checkpoint/tuned behavior → evaluate.

Check it: Use the named comparison dimensions to check the result; a demo, learner exercise and assessed project are distinct.

01 / Start withText/data02 / Comparearchitecture or training stage →checkpoint/tuned behavior03 / Useful outputevaluate.
One task, three points to compare.

This is a decision aid, not a promised assignment in every listed course.

Compare the course work and setup.

A demonstration, a learner exercise and individually reviewed work are different learning experiences. Check the practice and feedback each option actually describes.

Course and providerPracticeSetupTuition and format
Pretraining LLMsDeepLearning.AIWeb text is cleaned, packed and prepared for model pretraining; model configuration/training, depth-upscaling approaches and benchmarks complete the language-model engineering…Basic Python expected; LLM familiarity recommended.Free learning option. Price basis: Own page advertises free course access for a limited time during platform beta; not perpetual free access or a Pro…Online video lessons with advertised examples/resources; the page lists 6 code examples. Live cohort, mentoring and project access are not stated.
Post-training of LLMsDeepLearning.AIA pretrained model and curated datasets support supervised base-to-instruct tuning, chosen/rejected DPO assistant-identity changes and verifiable-reward GRPO math training.LLM basics expected; no formal Python admission requirement exposed.Free learning option. Price basis: Own page advertises free course access for a limited time during platform beta; not perpetual free access or a Pro…Online video lessons with advertised examples/resources; the page lists 3 code examples. Live cohort, mentoring and project access are not stated.
Reinforcement Fine-Tuning LLMs With GRPODeepLearning.AIWordle reasoning is framed as reinforcement fine-tuning; rewards, subjective-summary LLM judging, hacking penalties and GRPO loss are designed before launching hosted training…Intended for LLM fine-tuners/reasoning practitioners; exact formal programming admission unexposed.Free learning option. Price basis: Own page advertises free course access for a limited time during platform beta; not perpetual free access or a Pro…Online video lessons with advertised examples/resources; the page lists 1 code examples. Live cohort, mentoring and project access are not stated.
Build and Train an LLM with JAXDeepLearning.AIMini-story data is tokenized/batched for a 20 million-parameter MiniGPT architecture in JAX/Flax; Optax training and Orbax checkpoints precede the final pretrained-model…Python and basic machine-learning knowledge are recommended.Price: ask the provider. Price basis: Own page advertises Enroll Now and additional Pro quizzes/projects/accomplishment. Base lesson-access price and Pro…Online video lessons with advertised examples/resources; the page lists 4 code examples. Live cohort, mentoring and project access are not stated.
AI+ Engineer Practitioner™AI CERTsTrain neural networks, fine-tune language models for text classification, generate images with generative models, build pretrained/Hugging Face NLP pipelines and develop GUI…AI+ Data Practitioner™ or AI+ Developer Practitioner™ Certification: Completion is recommended for foundational knowledge. Python Programming…495 (currency not specified). Price basis: Issuer displays $495.00; dollar currency code and tax basis unestablished.Public individual self-study digital purchase: videos, podcasts, e-books/audiobooks, quizzes, AI Mentor and mobile access advertised.
Agentic Machine Learning Engineerneue fische / SPICED AcademyPrepare real data and train/evaluate models, then build a retrieval- and memory-equipped LLM tool. Implement a pure agent loop, refactor into frameworks, add sandboxed tools…Basic Python and foundational programming; no prior AI/ML required. Passing an initial assessment is required.Price: ask the provider. Price basis: Self-pay and deferred-payment routes advertised; amount unexposed. German education-voucher funding is conditional…A live, full-time remote cohort with coaches. The provider's schedule details conflict; confirm the timetable for your cohort.

Course options

Look beyond the title. Compare the project work, required accounts, software costs and type of help.

Browse all courses
1–6 of 6 courses
AI engineering

DeepLearning.AI

Pretraining LLMs

Web text is cleaned, packed and prepared for model pretraining; model configuration/training, depth-upscaling approaches and benchmarks complete the language-model engineering sequence.

Tuition
Free learning option. Price basis: Own page advertises free course access for a limited time during platform beta; not perpetual free access or a Pro…
Format
Online video lessons with advertised examples/resources; the page lists 6 code examples. Live cohort, mentoring and project access are not stated.
Practice
Web text is cleaned, packed and prepared for model pretraining; model configuration/training, depth-upscaling approaches and benchmarks complete the language-model engineering…
Setup
Basic Python expected; LLM familiarity recommended.
Course details ↗Provider access conditions apply
AI engineering

DeepLearning.AI

Post-training of LLMs

A pretrained model and curated datasets support supervised base-to-instruct tuning, chosen/rejected DPO assistant-identity changes and verifiable-reward GRPO math training.

Tuition
Free learning option. Price basis: Own page advertises free course access for a limited time during platform beta; not perpetual free access or a Pro…
Format
Online video lessons with advertised examples/resources; the page lists 3 code examples. Live cohort, mentoring and project access are not stated.
Practice
A pretrained model and curated datasets support supervised base-to-instruct tuning, chosen/rejected DPO assistant-identity changes and verifiable-reward GRPO math training.
Setup
LLM basics expected; no formal Python admission requirement exposed.
Course details ↗Provider access conditions apply
AI engineering

DeepLearning.AI

Reinforcement Fine-Tuning LLMs With GRPO

Wordle reasoning is framed as reinforcement fine-tuning; rewards, subjective-summary LLM judging, hacking penalties and GRPO loss are designed before launching hosted training jobs.

Tuition
Free learning option. Price basis: Own page advertises free course access for a limited time during platform beta; not perpetual free access or a Pro…
Format
Online video lessons with advertised examples/resources; the page lists 1 code examples. Live cohort, mentoring and project access are not stated.
Practice
Wordle reasoning is framed as reinforcement fine-tuning; rewards, subjective-summary LLM judging, hacking penalties and GRPO loss are designed before launching hosted training…
Setup
Intended for LLM fine-tuners/reasoning practitioners; exact formal programming admission unexposed.
Course details ↗Provider access conditions apply
AI engineering

DeepLearning.AI

Build and Train an LLM with JAX

Mini-story data is tokenized/batched for a 20 million-parameter MiniGPT architecture in JAX/Flax; Optax training and Orbax checkpoints precede the final pretrained-model chat/story-generation path.

Tuition
Price: ask the provider. Price basis: Own page advertises Enroll Now and additional Pro quizzes/projects/accomplishment. Base lesson-access price and Pro…
Format
Online video lessons with advertised examples/resources; the page lists 4 code examples. Live cohort, mentoring and project access are not stated.
Practice
Mini-story data is tokenized/batched for a 20 million-parameter MiniGPT architecture in JAX/Flax; Optax training and Orbax checkpoints precede the final pretrained-model…
Setup
Python and basic machine-learning knowledge are recommended.
Course details ↗Provider access conditions apply
Apps and models

AI CERTs

AI+ Engineer Practitioner™

Module 1: Foundations of Artificial Intelligence; Module 2: Introduction to AI Architecture; Module 3: Fundamentals of Neural Networks; Module 4: Applications of Neural Networks; Module 5: Significance of…

Tuition
495 (currency not specified). Price basis: Issuer displays $495.00; dollar currency code and tax basis unestablished.
Format
Public individual self-study digital purchase: videos, podcasts, e-books/audiobooks, quizzes, AI Mentor and mobile access advertised.
Practice
Train neural networks, fine-tune language models for text classification, generate images with generative models, build pretrained/Hugging Face NLP pipelines and develop GUI…
Setup
AI+ Data Practitioner™ or AI+ Developer Practitioner™ Certification: Completion is recommended for foundational knowledge. Python Programming…
Course details ↗Provider access conditions apply
AI engineering

neue fische / SPICED Academy

Agentic Machine Learning Engineer

Python/data analysis; classification/regression/ensembles; deep learning; LLM APIs and RAG; persistent knowledge; agent loops and stateful workflows; multi-agent systems; evaluation/safety; three-week deployed…

Tuition
Price: ask the provider. Price basis: Self-pay and deferred-payment routes advertised; amount unexposed. German education-voucher funding is conditional…
Format
A live, full-time remote cohort with coaches. The provider's schedule details conflict; confirm the timetable for your cohort.
Practice
Prepare real data and train/evaluate models, then build a retrieval- and memory-equipped LLM tool. Implement a pure agent loop, refactor into frameworks, add sandboxed tools…
Setup
Basic Python and foundational programming; no prior AI/ML required. Passing an initial assessment is required.
Course details ↗Provider access conditions apply

Related learning decisions