khirotaka

Architecture

ReActなどのエージェントシステムの大まかな処理はこのようになっている

sequenceDiagram
    Agent ->> LLM: プロンプトを送信
    LLM -->> Agent: LLMの出力
    Agent ->> Tool: Actionの実行
    Tool ->> Environment: Toolを実行

khirotaka

• sheldon

[plugins.zsh-autosuggestions]
github = "zsh-users/zsh-autosuggestions"

khirotaka

use std::mem;


fn main() {
    let mut a: Vec<i32> = vec![1, 2, 3];
    let mut b: Vec<i32> = vec![4, 5, 5];

    println!("i32 size of {}", mem::size_of::<i32>());

    println!("var a: {:?}", a.as_ptr());

khirotaka

set number

" シンタックスハイライトの設定
syntax on

filetype on
filetype indent on
filetype plugin indent on
augroup vimrc
    autocmd!

khirotaka

fpath+=~/.zfunc
autoload -U compinit
compinit


alias ls="ls -pG"
export LSCOLORS=gxfxcxdxbxegedabagacad

# prompt
PROMPT="%F{2}%n@%m:%f%F{4}%~%f$ "

khirotaka

Install Miniconda on server

Download

$ curl -O https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

Run install script

khirotaka

FROM pytorch/pytorch:0.4.1-cuda9-cudnn7-devel

RUN apt-get update \
    && apt-get install -y  --no-install-recommends \
    build-essential \
    vim \
    python-pil \
    python-matplotlib \
    python-pygraphviz \
    default-jdk \

khirotaka

set number
imap <c-j> <esc>


"シンタックスハイライトの設定
syntax on


"タブ の大きさをスペース 4つ分に設定
set expandtab

khirotaka

• Discovering Semantic Motifs in the Time Series

• Time Series Mining in the Face of Fast Moving Streams using a Learned Approximate Matrix Profile

• Discovering Subdimensional Motifs of Different Length in Large-Scale Multivariate Time Series

• Exploiting Time Series Consensus Motifs to Find Structure in Time Series Sets

• A Wasserstein Subsequence Kernel for Time Series

  • GitHub

• MTEX-CNN: Multivariate Time series EXplanations for Predictions with Convolutional Neural Networks

khirotaka

見出し1

見出し2

見出し3

見出し4

見出し5

見出し6

---

hello,