A very brief introduction to DQN, AI Web interfaces and LLM Embeddings.
Efren Yevale Varela
83f624e5c1
Added links
|
%!s(int64=2) %!d(string=hai) anos | |
|---|---|---|
| Embeddings | %!s(int64=2) %!d(string=hai) anos | |
| Links | %!s(int64=2) %!d(string=hai) anos | |
| Milvus | %!s(int64=2) %!d(string=hai) anos | |
| Pong | %!s(int64=2) %!d(string=hai) anos | |
| Taxi | %!s(int64=2) %!d(string=hai) anos | |
| .gitignore | %!s(int64=2) %!d(string=hai) anos | |
| LICENSE.md | %!s(int64=2) %!d(string=hai) anos | |
| README.md | %!s(int64=2) %!d(string=hai) anos | |
| requirements.txt | %!s(int64=2) %!d(string=hai) anos |
README.md
AI Session
The objective is to give a very brief introduction to DQN training using games (just to talk about theory), present OpenSource Web interfaces and create LLM Embeddings to ask questions about given documents.
Things to cover:
- Simple theory of Q-learning, with a practical example using the a Taxi game.
- Simple theory of Proximal Policy Optimization, with a practical example using a Pong game.
- OpenSource Web interfaces available for Stable Diffusion, Inference and Embeddings.
- A practical example on how to create and use LLMs and Embeddings using a Python script.
In no way should any of this be considered as a complete solution, the goal is just to provide enough elements for a start so all participants can grow from there.