Description

This repo contains quantized files of Toppy-Mix-4x7B.

This project was originaly a request from BlueNipples : link

The difference with the OG Toppy-M is the addition of Noromaid with the 3 models used to do Toppy-M, to have all the model as Expert in this MoE model, and not just merged one into one.

WARNING: ALL THE "K" GGUF QUANT OF MIXTRAL MODELS SEEMS TO BE BROKEN, PREFER Q4_0, Q5_0 or Q8_0!

Models and loras used

Prompt template: Alpaca

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

### Instruction:
{prompt}

### Response:

If you want to support me, you can here.

Downloads last month
45
GGUF
Model size
24.2B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

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