Downloads · 30 days
12
7% of all-time downloads
madgrizzle/starsnatched-MemGPT-DPO-MoE-test-exl2
starsnatched-MemGPT-DPO-MoE-test-exl2 is a text generation model from madgrizzle. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is a test release of DPO version of MemGPT Language Model.
Downloads · 30 days
12
7% of all-time downloads
All-time downloads
179
Public
Repo size
12.6 GB
Likes
0
Public
Click a slice to open those files.
.safetensors12.6 GB · 100%
From the Hugging Face model README
This is a test release of DPO version of MemGPT Language Model.
This model has been quantized using exllama for 8-bits.
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.
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|>
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!
The model is designed to be used as the base model for MemGPT agents.
The model may exhibit unreliable, unsafe, or biased behaviours. Please double check the results this model may produce.