EP48: 9-hour crash course curriculum for learning to build LLM applications.

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

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

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

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

Resources:

📺 30m: Simple Introduction to LLMs (Matthew Berman) 👉https://bit.ly/3KmQxPW

📖 40m: A Very Gentle Introduction to LLMs without the Hype (Mark Riedl) 👉https://bit.ly/3yEJzmO

📺 10m: How do LLMs work? Next Word Prediction with the Transformer Architecture Explained (Louis-François Bouchard) 👉https://bit.ly/4bERFub

📺 10m: What is Semantic Search? (Luis Serrano) 👉https://bit.ly/3yBOKDU

---

𝗣𝗔𝗥𝗧 𝟮 - 𝗧𝗥𝗔𝗡𝗦𝗙𝗢𝗥𝗠𝗘𝗥 𝗔𝗥𝗖𝗛𝗜𝗧𝗘𝗖𝗧𝗨𝗥𝗘 (1h 30m)

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

Resources:

📺 30m: But what is a GPT? Visual intro to transformers (3Blue1Brown) 👉https://bit.ly/45c2aTp

📺 20m: Sequence-to-Sequence (seq2seq) Encoder-Decoder Neural Networks, Clearly Explained! (Josh Starmer) 👉https://bit.ly/3KuI90F

📺 10m: The Attention Mechanism (Luis Serrano) 👉https://bit.ly/3yIvMvD

📺 15m: Transformer Models (Luis Serrano) 👉https://bit.ly/4aD62Ox

📺 15m: Generative Pre-trained Transformer (GPT) (Databricks) 👉https://bit.ly/458I7oP

---

𝗣𝗔𝗥𝗧 𝟯 - 𝗣𝗥𝗢𝗠𝗣𝗧 𝗘𝗡𝗚𝗜𝗡𝗘𝗘𝗥𝗜𝗡𝗚 (2h 0m)

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

Resources:

📺 60m: Prompt Engineering Overview (Elvis Saravia) 👉https://bit.ly/4bUGX37

📖 90m: Prompt Engineering Guide (DAIR) 👉https://bit.ly/3V7eb87

📖 30m: Brex's Prompt Engineering Guide (Brex) 👉https://bit.ly/3yGt9ul

⚒ 0m: LangChain Hub 👉https://bit.ly/3VmP2HJ

---

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

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

Resources:

📺 30m: The LangChain Cookbook - Beginner Guide To 7 Essential Concepts (Greg Kamradt) 👉https://bit.ly/3wXCu02

📺 30m: The LangChain Cookbook Part 2 - Beginner Guide To 9 Use Cases (Greg Kamradt) 👉https://bit.ly/3KnIQZL

⚒ 0m: Learn LangChain (Greg Kamradt) 👉https://bit.ly/3wNr5jB

📖 30m: Advanced RAG (Hugging Face) 👉https://bit.ly/3yS0ouo

📺 5m: Vector databases are so hot right now. WTF are they? (Fireship) 👉

📺 10m: Question A 300 Page Book (w/ OpenAI + Pinecone) (Greg Kamradt) 👉https://bit.ly/3VmHEw2

📺 20m: Talk to Your Documents, Powered by Llama-Index (Prompt Engineering) 👉https://bit.ly/4bWJEAA

📺 30m: From OpenAI Function Calling to LangChain Agents (Automata Learning Lab) 👉https://bit.ly/4bZpDcJ

---

𝗣𝗔𝗥𝗧 𝟱 - 𝗙𝗜𝗡𝗘𝗧𝗨𝗡𝗜𝗡𝗚 (1h 30m)

Feature-based finetuning, LoRA, RLHF.

Resources:

📖 15m: Finetuning LLMs (Sebastian Raschka) 👉https://bit.ly/3Kmhxz9

📖 15m: Fine Tuning vs. Prompt Engineering LLMs (Niels Bantilan) 👉https://bit.ly/4aDJf4V

📺 30m: Reinforcement Learning from Human Feedback: From Zero to chatGPT (Hugging Face) 👉https://bit.ly/3KJ0UxT

📖 15m: Complete Guide On Fine-Tuning LLMs using RLHF (Labellerr) 👉https://bit.ly/3R9I8TH

📖 15m: LoRA (Hugging Face) 👉https://bit.ly/4aD5S9T

#AI #MachineLearning #DeepLearning #InnovationTechnology #ArtificialIntelligence #GenerativeAI #LLM