Quantization made by Richard Erkhov.

MLewd-ReMM-L2-Chat-20B - GGUF

license: cc-by-nc-4.0 tags:

First :

Inverted:

Precise:

PreciseInverted:

Part1 = ReMM v2.1 merged /w MLewd low weight to keep consistency. I call this "dilution" and result show consistency and coherency without repeat/loop beside the small amount of duplicated datas.

The goal is to find the best way to interlace layers the best way possible to have a sweetspot between 13B and +30B.

Normal/Inverted is by chunk of 16 layers and Precise/PreciseInverted is by chunk of 8 layers.

All the models are made of 64(+1) layers. Need testing.

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

### Instruction:
{prompt}

### Response:

Detailed results can be found here