January 30, 2023 In this post, we'll implement a GPT from scratch in just 60 lines of numpy. We'll then load the trained GPT-2 model weights released by OpenAI into our implementation and generate some text. Note: This post assumes familiarity with Python, NumPy, and some basic experience with neural networks. This implementation is for educational purposes, so it's missing lots of features/improv
A 100x speedup with unsafe Python
We're going to speed up some numpy code by 100x using "unsafe Python." Which is not quite the same as unsafe Rust, but it's a bit similar, and I'm not sure what else to call it... you'll see. It's not something you'd use in most Python code, but it's handy on occasion, and I think it shows "the nature of Python” from an interesting angle. So let's say you use pygame to write a simple game in Pytho
はじめての自然言語処理 ELYZA 日本語 Llama 2 指示応答モデルのファインチューニングと vLLM での推論 | オブジェクトの広場
今回は Elyza さんの日本語 Llama 2 指示応答モデルをファインチューニングし、vLLM にデプロイして高速に推論してみます。70 億パラメータモデルならギリギリ Tesla T4 x 1 の構成でも float16 で動かせるかと思ったのですが、どうだったでしょうか。vLLM には OpenAI 互換の API インタフェースも備えているので、ついでに LangChain からも接続してみたり。 1. はじめに 今回は Elyza さんが公開されている大規模指示応答言語モデルである、ELYZA-japanese-Llama-2-7b-fast-instruct1 をファインチューニングして vLLM で推論してみます。 そんな訳で今回あまり書くことがなく、動かし方だけサラっと書いて「動きましたー。では良いお年を～。」で締めることにします。 しかし、時代感覚無視の隔月連載でネタを
Reindex, Transform, and Aggregate datasets using pandas Library
Most of the time, the dataset we will get from the business will be dirty and cannot be used straight forward to train machine learning models. Therefore, we must treat the dataset and bring it to the desired form to input it into an algorithm. This tutorial discusses reindexing, transforming, and aggregating datasets in Pandas. What are Reindexing, Transforming, and Aggregating?Reindexing, transf
FreeSimpleGUI
FreeSimpleGUI User Interfaces for Humans - Transforms tkinter, Qt, Remi, WxPython into portable people-friendly Pythonic interfaces The Call Reference Section Moved to here This manual is under construction as we adapt changes to FreeSimpleGUI and make simplifications. Some links may not work as expected. References to "PySimpleGUI" can safely be assumed to be interchangable with "FreeSimpleGUI" J
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
GPT in 60 Lines of NumPy | Jay Mody