GGUF
Not-For-All-Audiences
nsfw
Merge
Inference Endpoints
Edit model card

Description

This repo contains quantized files of LewdGem-40B, a MoE model of the 4 best llama2 model of Undi95 and NeverSleep repo.

Since I don't have a lot of time or ressource to train new model at the moment, I didn't wanted to let my repo dry, so I got the idea to make a MoE of my most liked/used ERP model (and the last Noromaid supporting Alpaca).

I moved out correctly and I'm comfy in my new home, thank you all for the support!

Models used

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{system prompt}

### Input:
{prompt}

### Response:

If you want to support me, you can here.

Downloads last month
91
GGUF
Model size
38.5B params
Architecture
llama

4-bit

5-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .