https://github.com/llami-team/gpt-torch

Compress the HTML as much as possible for LLM to inference.
https://github.com/llami-team/gpt-torch

gpt html korea korean llm tokenizer

Last synced: 5 months ago
JSON representation

Compress the HTML as much as possible for LLM to inference.

• Host: GitHub
• URL: https://github.com/llami-team/gpt-torch
• Owner: llami-team
• Created: 2024-04-20T07:28:41.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-08-22T07:06:10.000Z (about 1 year ago)
• Last Synced: 2024-12-19T15:51:45.113Z (10 months ago)
• Topics: gpt, html, korea, korean, llm, tokenizer
• Homepage: https://gpt-torch.vercel.app/
• Size: 1.95 KB
• Stars: 42
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
> [!NOTE]

> gpt-torch is currently temporarily available to collaboration teams only.  If you have a request, please contact contact@llami.net

![gpt-torch Open Graph Image](https://html-torch.vercel.app/og.png)

# gpt-torch 🔥

`gpt-torch` is a library designed to clean up HTML by removing everything but the tags meaningful to Large Language Models (LLMs). It strips away unnecessary scripts, styles, attributes, and more to tidy up HTML content.

https://gpt-torch.vercel.app