Getting started LLM for workshop

How to use the LLMs

  • Prompt Engineering
  • Retrieval Augmented Generation (RAG)
  • Fine-tuning
  • Training your own Foundation Model(FM) from scratch

Vector databases

Knowledge

  • Referred to as “prompts”. Designing a prompt is essentially how you “program” a large language model model
  • Plugins can be “eyes and ears” for language models
  • Using commands to instruct the model what you want to achieve, such as “Write”, “Classify”, “Summarize”, “Translate”, “Order”
  • Foundation model (FM) – An AI model with a large number of parameters and trained on a massive amount of diverse data. A foundation model can generate a variety of responses for a wide range of use cases
  • Agent – An application that carry out orchestrations through cyclically interpreting inputs and producing outputs by using a foundation model. An agent can be used to carry out customer requests. For more information
  • Retrieval augmented generation (RAG) – The process of querying and retrieving information from a data source in order to augment a generated response to a prompt. For more information

Prompt example

  • Give a demonstrations
 1
 2Q: What is prompt engineering?
 3A: It's a laugnauge for LLM to interactive
 4
 5This is awesome! // Positive
 6This is bad! // Negative
 7Wow that movie was rad! // Positive
 8What a horrible show! //
 9
10Classify the text into neutral, negative, or positive
11Text: I think the food was okay.
12Sentiment:
13
14### Instruction ###
15Translate the text below to Spanish:
16Text: "hello!"

AutoGpt getting started

  • Fork the offical repo https://github.com/Significant-Gravitas/Auto-GPT.git
  • Clone the yourself repo git clone https://github.com/Significant-Gravitas/Auto-GPT.git
  • Setting up the project
1cd Auto-GPT
2# create you agent
3./run agent create YOUR_AGENT_NAME
4# start you agent
5./run agent start YOUR_AGENT_NAME
6# to stop agent
7./run agent stop

GPTS Limits

Model Maximum text length
gpt-3.5-turbo 4,096 tokens (~5 pages)
gpt4 8,192 tokens (~10 pages)
gpt4-32k 32,768 tokens (~40 pages)

Generative AI application framework

Reference

Opensource LLM