Generative AI & LLMs
Large language models, prompting, retrieval (RAG), fine-tuning and image generation.
Expert
Research-level depth and specialist material.
Ettin Suite: SoTA Paired Encoders and Decoders
An article from Hugging Face on Ettin Suite: SoTA Paired Encoders and Decoders. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Hugging Face
MCP for Research: How to Connect AI to Research Tools
An article from Hugging Face on MCP for Research: How to Connect AI to Research Tools. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Hugging Face
Building Deep Research: How we Achieved State of the Art
An article from Hugging Face on Building Deep Research: How we Achieved State of the Art. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Hugging Face
SOTA OCR with Core ML and dots.ocr
An article from Hugging Face on SOTA OCR with Core ML and dots.ocr. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Hugging Face
MosaicLeaks: Can your research agent keep a secret?
An article from Hugging Face on MosaicLeaks: Can your research agent keep a secret. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Hugging Face
Reward Hacking in Reinforcement Learning
An article from Lilian Weng on Reward Hacking in Reinforcement Learning. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Lilian Weng
Harness Engineering for Self-Improvement
An article from Lilian Weng on Harness Engineering for Self-Improvement. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Lilian Weng
Scaling Laws, Carefully
An article from Lilian Weng on Scaling Laws, Carefully. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Lilian Weng
Why We Think
An article from Lilian Weng on Why We Think. In-depth material for learners already confident in Generative AI & LLMs. It opens on the publisher's site in a new tab.
Lilian Weng
Building and Evaluating Advanced RAG Applications
Advanced retrieval methods such as sentence-window and auto-merging retrieval, and how to measure RAG quality.
DeepLearning.AI and LlamaIndex
Let's Build GPT: From Scratch, in Code, Spelled Out
Karpathy writes a small GPT in PyTorch line by line, following the 'Attention Is All You Need' design.
Andrej Karpathy
Let's Build the GPT Tokenizer
Builds a byte-pair-encoding tokenizer from scratch and explains many odd LLM behaviours that come from tokenisation.
Andrej Karpathy