Model Description

This repository contains a MoE (Mixture of Experts) model of Mistral 7B Instruct. It has 2 experts per token. This model is specifically designed for function calling in MemGPT. It demonstrates comparable performances to GPT-4 when it comes to working with MemGPT.

Key Features

Function calling
Dedicated to working with MemGPT
Supports medium-length context, up to sequences of 8,192

Prompt Format

This model uses ChatML prompt format:

<|im_start|>system
{system_instruction}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>

Usage

This model is designed to be ran on multiple backends, such as oogabooga's textgen WebUI. Simply install your preferred backend, and then load up this model. Then, configure MemGPT using memgpt configure, and chat with MemGPT via memgpt run command!

Model Details

Developed by: @starsnatched
Model type: This repo contains a language model based on the transformer decoder architecture.
Language: English
Contact: For any questions, concerns or comments about this model, please contact me at Discord, @starsnatched.

Training Infrastructure

Hardware: The model in this repo was trained on 2x A100 80GB GPUs.

Intended Use

The model is designed to be used as the base model for MemGPT agents.

Limitations and Risks

The model may exhibit unreliable, unsafe, or biased behaviours. Please double check the results this model may produce.