A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer
MIT License
A school for camelids
Code and documentation to train Stanford's Alpaca models, and generate the data.
Aligning pretrained language models with instruction data generated by themselves.
Alpaca dataset from Stanford, cleaned and curated
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
structured outputs for llms
Creating Intelligent Terminal Apps with ChatGPT and LLM Models
Toolkit for creating, sharing and using natural language prompts.
SQL functions for calling OpenAI APIs