r2d4/rellm
Exact structure out of any language model completion.
This tool helps developers working with large language models (LLMs) ensure their model outputs have a precise, predictable structure. By defining a regular expression pattern, you can guide the LLM to generate completions that adhere to specific formats, such as JSON, dates, numbers, or custom sentence templates. This is useful for anyone building applications where reliable, structured data extraction from free-form text generation is critical.
514 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need an LLM to consistently produce output in a specific, exact format, like a valid JSON object, a date, or a precise sentence structure.
Not ideal if you need flexible, creative, or unconstrained text generation where precise output formatting is not a primary concern.
Stars
514
Forks
23
Language
Python
License
MIT
Category
Last pushed
Aug 10, 2023
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/r2d4/rellm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM