Question 1

Is the Open Source AI Academy free?

Accepted Answer

Yes, 100% free. No sign-up, no credit card. All 15 modules, 18 lessons, and 45 quiz questions are accessible immediately. Your progress saves locally in your browser.

Question 2

What topics does the Open Source AI Academy cover?

Accepted Answer

The course covers Transformer architecture, Meta Llama 4, Mistral, DeepSeek, Qwen, Gemma, Hugging Face, quantization (GGUF, AWQ, GPTQ, EXL2), Ollama, llama.cpp, vLLM, SGLang, LoRA/QLoRA fine-tuning, pre-training from scratch, RLHF/DPO/GRPO alignment, and production MLOps with Docker and Kubernetes.

Question 3

What is vLLM?

Accepted Answer

vLLM is the industry-standard engine for high-throughput production LLM serving. It uses PagedAttention for efficient GPU memory management and continuous batching for >90% GPU utilization.

Question 4

Do I need expensive hardware to run open-source models?

Accepted Answer

No. Many models can run on consumer GPUs (e.g., RTX 4090) or even CPUs via llama.cpp. The course covers deployment strategies for every budget, from Raspberry Pi edge devices to multi-GPU production clusters.

Stage	Purpose	Technique
1. SFT	Instruction following, format, conversational style	Supervised Fine-Tuning on instruction datasets
2. Preference	Align with human values and preferences	DPO, KTO, SimPO (no reward model needed)
3. RL	Push beyond training data for reasoning	GRPO, RLVR (for math/code verification)

Method	Complexity	Memory	Best For
RLHF (PPO)	High (needs reward model + critic)	~4x model size	Classic, proven approach
DPO	Low (direct from preference pairs)	~2x model size	Simple, stable preference alignment
GRPO	Medium (group-wise comparison)	~2x model size	Reasoning, no critic needed

The Alignment Stack: RLHF → DPO → GRPO

Modern Post-Training Pipeline

The Three Stages

Technique Comparison