🔄 Transformers

Hugging Face's official channel — workshops on transformers, fine-tuning, agents, multimodal. {description}

Umar Jamil's deep dives — building LLaMA, Mistral, BERT, attention from scratch in PyTorch. {description}

freeCodeCamp's Hugging Face crash course — using transformers, pipelines, and the Hub. {description}

Yannic Kilcher's deep-dive walkthroughs of major AI papers — best resource for understanding the latest research. {description}

Karpathy builds a byte-pair-encoding tokenizer from scratch — explains the most misunderstood part of LLMs. {description}

Karpathy builds a GPT model from scratch in code — the canonical hands-on intro to transformer training. {description}

Andrej Karpathy's legendary YouTube series — build neural networks and a GPT from scratch, line by line, in PyTorch. {description}

NPTEL's deep learning for NLP course — word embeddings, RNNs, attention, transformers. {description}

Graham Neubig's CMU NLP course — modern LLMs, tokenization, attention, alignment, evaluation. {description}

Stanford's deep dive into building LLMs end-to-end — tokenization, architecture, training, alignment. {description}