Mix.install([
{:kino, "~> 0.16.1"}
], consolidate_protocols: false)
defmodule ElixirAiAgent do | |
@moduledoc """ | |
A minimal ai agent implementation showcasing how simple it is to build AI agents in Elixir. | |
Combines agent logic and server management in one module. | |
""" | |
use GenServer | |
alias LangChain.Chains.LLMChain | |
alias LangChain.Message |
This aims to be factual information about the size of large language models. None of this document was written by AI. I do not include any information from leaks or rumors. The focus of this document is on base models (the raw text continuation engines, not 'helpful chatbot/assistants'). This is a view from a few years ago to today of one very tiny fraction of the larger LLM story that's happening.
- GPT-2,-medium,-large,-xl (2019): 137M, 380M, 812M, 1.61B. Source: openai-community/gpt2. Trained on the unreleased WebText dataset said to 40GB of Internet text - I estimate that to be roughly 10B tokens. You can see a list of the websites that went into that data set here domains.txt.
- GPT-3 aka davinci, davinci-002 (2020): 175B parameters. There is a good breakdown of how those parameters are 'spent' here [How d
Use list_generators
to list available generators when available, otherwise mix help
. If you have to run generator tasks, pass --yes
. Always prefer to use generators as a basis for code generation, and then modify afterwards.
Use tidewave MCP tools when available, as they let you interrogate the running application in various useful ways.
View Markup Language (VML) is a markup language derived from SGML, designed to represent composable UI frameworks for unidirectional, server-driven rendering. This specification defines the conversion from a server-side view model, such as SwiftUI, to VML.
Specification Note 1.1: Scope The VML specification is concerned exclusively with the structure and rendering of views. It is a unidirectional standard (server-to-client). Mechanisms for handling user interactions, actions, and client-to-server state changes are explicitly outside the scope of this document.
config :phoenix, :json_library, ErlJson |
#!/usr/bin/env bash | |
# Abort sign off on any error | |
set -e | |
# Start the benchmark timer | |
SECONDS=0 | |
# Repository introspection | |
OWNER=$(gh repo view --json owner --jq .owner.login) |
#!/usr/bin/env -S bash -c "docker run -p 8080:8080 -it --rm \$(docker build --progress plain -f \$0 . 2>&1 | tee /dev/stderr | grep -oP 'sha256:[0-9a-f]*')" | |
# syntax = docker/dockerfile:1.4.0 | |
FROM node:20 | |
WORKDIR /root | |
RUN npm install sqlite3 |