Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

gpt-llm-trainer is a constrained agent -- meaning its behavior is highly-controlled, leading to better results than open-ended agents. It chains together lots of GPT-4 calls that work together to create a great dataset for you.

How it works, in a nutshell: - The user describes the model they want Ex: "A model that writes Python functions" - GPT-4 generates a dataset to train on - We process the dataset, and train a model!

It's crazy how quickly you can go from an idea to a fully-trained model with this system. And the resulting models are really good!

If you'd like to try it or contribute, check out the Github repo or the Colab notebook:

One suggestion is you should change it from NousResearch/Llama-2 Chat model to llama-2's base model. Training over that terrible chat model doesn't seem to be wise imo

@far__el Matt you're on fire 😂 did you' JUST launch GPT-prompt engineer AND a product hunt launch of personal AI agent?

@far__el Haha thanks! I’m only able to do all of this by leveraging AI to help :)

This is very cool. What is your recommendation on a use case that is well suited for this (i.e. training a task specific LLM vs. using hosted LLM)?

I'm still exploring the possibilities, so right now I'm not too sure! Let me know if you find anything interesting. That said, using a model trained like this would be significantly cheaper than using most hosted LLMs :)

Can you give examples of models' performance trained using this tool?

I threw this together quickly last night, so I haven't had the chance to test it extensively. But from the few tests I did, if you have GPT-4 generate 200+ examples, it's actually pretty good!