RLHF Courses and Certifications

Yacine Mahdid

Exploring GRPO Through the RAFT Algorithm - RLHF and RLVR

Dive into GRPO's mechanics through RAFT algorithm analysis, comparing RLHF and RLVR paradigms from 2023-2025 studies to develop simplified reinforcement learning approaches for LLMs.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Amazon Web Services;  Amazon

AWS SimuLearn: Fine-Tune a Base Model with RLHF

Hands-on experience with AI-powered simulations to design and implement AWS solutions for fine-tuning base models using RLHF. Practice communication skills while working with services like SageMaker, API Gateway, DynamoDB, and S3.

• AWS Skill Builder
• 1 hour
• On-Demand
• Paid Course

LLMs from Scratch - Practical Engineering from Base Model to PPO RLHF

Master building complete large language models from scratch using pure PyTorch, covering transformer architecture, training, scaling, MoE, fine-tuning, and RLHF techniques.

• freeCodeCamp
• 6 hours 6 minutes
• On-Demand
• Free Video

Mastering ChatGPT (AI) and PowerPoint presentation

455 ratings at Udemy

Combined Artificial intelligence to create presentation

• Udemy
• 5 hours 1 minute
• On-Demand
• Paid Course

LLM Fine Tuning Fundamentals + Fine tune OpenAI GPT model

364 ratings at Udemy

Learn the fundamentals of LLM and LLM Fine Tuning. Hands-On sessions to Fine tune OpenAI GPT model with custom data.

• Udemy
• 3 hours 27 minutes
• On-Demand
• Paid Course

Serrano.Academy

Reinforcement Learning for Large Language Models - RLHF, PPO, DPO, and GRPO

Discover how to fine-tune LLMs using RLHF, PPO, DPO, and GRPO techniques with practical deep reinforcement learning methods for transformer models.

• YouTube
• 2 hours 28 minutes
• On-Demand
• Free Video

Microcredential

LLM Application Engineering and Development Certification

13 ratings at Coursera

Master LLM application engineering with LangChain workflows, fine-tuning techniques, and evaluation benchmarks to build scalable GenAI solutions for real-world deployment.

• Coursera
• 4 weeks, 10 hours a week
• On-Demand
• Paid Course
• 4 courses

Whizlabs

NVIDIA: Large Language Models and Generative AI Deployment

Master the deployment and optimization of Large Language Models through hands-on training in model fundamentals, GPU-accelerated training techniques, PEFT methods, and ONNX-based monitoring strategies.

• Coursera
• 4 hours 24 minutes
• On-Demand
• Paid Course

Microcredential

Quick Start Guide to Large Language Models (LLMs)

Master building and deploying GPT, Llama, T5, and BERT at scale with step-by-step guidance, real-world case studies, fine-tuning techniques, and practical applications.

• Coursera
• 4 weeks, 5 hours a week
• On-Demand
• Paid Course
• 3 courses

Alberta Machine Intelligence Institute Microcredential

Generative AI Essentials

Discover how generative AI models work, master prompt engineering, and develop ethical frameworks for responsible AI deployment across text and image generation.

• Coursera
• 4 weeks, 10 hours a week
• On-Demand
• Paid Course
• 3 courses

Board Infinity

Mastering DeepSeek: From Architecture to Application

Master DeepSeek's architecture, deployment, and practical applications through hands-on training. From API integration to RAG pipelines, coding workflows, and model fine-tuning for developers and AI enthusiasts.

• Coursera
• 17 hours 17 minutes
• On-Demand
• Paid Course

Quick Start Guide to Large Language Models (LLMs): Unit 3

Master advanced LLM architectures, multimodal integration, reinforcement learning alignment, fine-tuning optimization, and cloud deployment strategies for high-performing models.

• Coursera
• 8 hours 7 minutes
• On-Demand
• Paid Course

Discover AI

Coding RLHF on LLama 2 with LoRA, 4-bit Quantization, TRL and DPO

Master advanced LLM fine-tuning techniques using RLHF, implementing DPO and PPO methods on Llama models with 4-bit quantization and LoRA for optimized performance and human feedback integration.

• YouTube
• 36 minutes
• On-Demand
• Free Video

MLOps.community

Building and Curating Datasets for RLHF and LLM Fine-tuning

Learn effective strategies for dataset construction, curation, and annotation to enhance RLHF and LLM models using Argilla's open-source data platform for integrating human and machine feedback.

• YouTube
• 59 minutes
• On-Demand
• Free Video

Discover AI

CriticGPT: Understanding RLHF and Force Sampling Beam Search Optimization

Dive into OpenAI's innovative CriticGPT algorithm, exploring how RLHF and Force Sampling Beam Search optimize language models and enhance their reliability.

• YouTube
• 26 minutes
• On-Demand
• Free Video