9-hour course to build LLM applications

Here's a 9-hour crash course curriculum for learning to build LLM applications. All resources are free.
Build LLM application

𝗣𝗔𝗥𝗧 𝟭 - 𝗔 𝗚𝗘𝗡𝗧𝗟𝗘 𝗜𝗡𝗧𝗥𝗢 𝗧𝗢 𝗟𝗟𝗠𝗦 (1h 30m)

Intro & overview of language models, next-word prediction, embeddings, cosine similarity, semantic search:

📺 30m: Simple intro (MBerm)
📖 40m: llms nohype (MRied)
📺 10m: Next wrd prd (LBouc)
📺 10m: Sem search (LSerr)


𝗣𝗔𝗥𝗧 𝟮 - 𝗧𝗥𝗔𝗡𝗦𝗙𝗢𝗥𝗠𝗘𝗥 𝗔𝗥𝗖𝗛𝗜𝗧𝗘𝗖𝗧𝗨𝗥𝗘 (1h 30m)

Encoder-decoder architecture, masking, attention, transformers, GPTs:

📺 30m: Visual llm (3Blu1Br)
📺 20m: Enc-Dec (JStarm)
📺 10m: Attention (LSerr)
📺 15m: Transformers (LSerr)
📺 15m: GPTs (DataBrks)


𝗣𝗔𝗥𝗧 𝟯 - 𝗣𝗥𝗢𝗠𝗣𝗧 𝗘𝗡𝗚𝗜𝗡𝗘𝗘𝗥𝗜𝗡𝗚 (2h 0m)

Zero/one/few-shot, chain-of-thought, self-consistency, generated knowledge, prompt chaining, ReAct:

📺 60m: PE Overview (ESarav)
📖 90m: Prompt Eng (DAIR)
📖 30m: PE Guide (Brex)
⚒️ 0m: LangChain Hub


𝗣𝗔𝗥𝗧 𝟰 - 𝗖𝗛𝗔𝗜𝗡𝗜𝗡𝗚, 𝗥𝗔𝗚, 𝗩𝗘𝗖𝗧𝗢𝗥 𝗗𝗕𝗦, 𝗔𝗚𝗘𝗡𝗧𝗦 (2h 30m)

Langchain, RAG, vector databases, LlamaIndex, Open AI functions:

📺 30m: LngCh ckbk1 (GKam)
📺 30m: LngCh ckbk2 (GKam)
⚒️ 0m: LngCh tutorials (GKam)
📖 30m: Adv RAG (HugFace)
📺 5m: Vector dbs (Fireshp)
📺 10m: LC+Pinecone (GKam)
📺 20m: LlamaIdx (engprmpt)
📺 30m: OpenAI fn/agnt (auto)


𝗣𝗔𝗥𝗧 𝟱 - 𝗙𝗜𝗡𝗘𝗧𝗨𝗡𝗜𝗡𝗚 (1h 30m)

Feature-based finetuning, LoRA, RLHF:

📖 15m: Finetuning (SRasc)
📖 15m: FT v PrmpEng (NBant)
📺 30m: RLHF intro (HugFac)
📖 15m: RLHF guid (Lblerr)
📖 15m: LoRA (HugFac)

Curated by Jack Blandin. Good luck!

About the author

Shinji

AI Evangelist. Digital twin at @aipill.io

AI Pill

Take AI 💊 Deep Dive Into The Coming Wave.

AI Pill

Great! You’ve successfully signed up.

Welcome back! You've successfully signed in.

You've successfully subscribed to AI Pill.

Success! Check your email for magic link to sign-in.

Success! Your billing info has been updated.

Your billing was not updated.