MLExpert Interview GuideInterview Guide Prompt EngineeringPrompt Engineering

AlgorithmsAlgorithms NewsletterNewsletter

Discord (opens in a new tab)

Prompt Engineering
Why is it Important?
Create Prompts
What is a Prompt?
Structure of an Effective Prompt
Example prompts
🔒 Input and Output Format
Large Language Models (LLMs)
What are LLMs and how do they work?
Tokens
Techniques for optimizing LLM performance
Common pitfalls to avoid
StableVicuna
OpenLLaMa
Falcon 180B
LLaVA - Large Multimodal Model
Prompting Techniques
Zero-shot Prompting
🔒 Few-shot Prompting
🔒 Chain-of-Thought Prompting
🔒 Prompt Tuning
Use Cases
Explain a Concept
🔒 Outline a Topic
🔒 Write Email
Write and Explain Code
🔒 Social Media Marketing
🔒 Summarization
Build Apps with LangChain
Introduction to LangChain
LangChain QuickStart with Llama 2
🔒 Load Custom Data with Loaders
Add AI with Models
🔒 Make LLMs Useful with Chains
🔒 Build Chatbots with Memory
🔒 Complex Tasks with Agents
Projects
Private Chatbot with Local LLM (Falcon 7B) and LangChain
Private GPT4All: Chat with PDF Files
🔒 CryptoGPT: Crypto Twitter Sentiment Analysis
🔒 Fine-Tuning LLM on Custom Dataset with QLoRA
🔒 Deploy LLM to Production
🔒 Support Chatbot using Custom Knowledge
🔒 Chat with Multiple PDFs using Llama 2 and LangChain
🔒 Fine-Tuning Llama 2 on Custom Dataset
🔒 Deploy Llama 2 to Production with RunPod
🔒 AutoGen - Build Powerful AI Agents
🔒 AutoGen Use Cases
MemGPT - Unlimited Context (Memory) for LLMs
Avanced Techniques
ChatGPT API
Reverse Prompt Engineering
Faster LLM Inference
Archive
LangChain Quickstart

Page Contents

Setup
Tokenizer
Generation Config
Generating Output
With Training Config
Loading in 4 Bit
Loading in 8 bit
torch.compile()
Batch Inference
Lit-Parrot
References

Prompt Engineering

Faster LLM Inference

MLExpert is loading...

© 2020-2023 MLExpert™ by Venelin Valkov. All Rights Reserved.