目录

LLMS

ChatGPT

LLaMA

ChatLLaMA

ChatGLM

Alpaca

  • Stanford Alpaca: An Instruction-following LLaMA Mode
  • alpaca_data.json contains 52K instruction-following data we used for fine-tuning the Alpaca model. This JSON file is a list of dictionaries, each dictionary contains the following fields:
    • instruction: str, describes the task the model should perform. Each of the 52K instructions is unique.
    • input: str, optional context or input for the task. For example, when the instruction is “Summarize the following article”, the input is the article. Around 40% of the examples have an input.
    • output: str, the answer to the instruction as generated by text-davinci-003.
  • Alpaca.cpp

Chinese-Vicuna

Guanaco

Colossal-AI

Open-Assistant

ChatRWKV

BELLE

Dolly

Koala

Baize

LMFlow

FreedomGPT

MiniGPT-4

AutoGPT

JARVIS

FastChat

通用工具

文生图

Midjourney

数据集

参考资料