Text Generation
Inference Endpoints

What is the base model of openchat ? Llama /mistral / custom ?

by StephanePop - opened


I'm interested in using OpenChat 3.5 for commercial applications, given its Apache 2.0 license.
However, I've observed that previous versions of OpenChat were developed on the Llama2 framework.

Does OpenChat 3.5 also rely on the Llama2 base?
Additionally, does the training mentioned on the model's page refer primarily to fine-tuning?

Thank you in advance for your answer

OpenChat org

This model is based on Mistral 7B (Apache-2.0 licensed). Besides, the training mentioned refers to fine-tuning.

I would like to uderstand one thing, the paper only mention a 13b model with llama-2-13b as its base model.
so if i understand correctly:

  1. openchat-13b (from the paper) -> base model llama-2-13b
  2. openchat 3.5 (this repo) -> base model Mistral 7b
OpenChat org

Yes, exactly. This release is based on Mistral 7b.

Alright, thank you for the great work.

Sign up or log in to comment