metadata

license: cc-by-nc-4.0
language:
  - en
pipeline_tag: text-generation
tags:
  - Merge

DaringMaid-20B-V1.1

Whats New?

This is an updated version of DaringMaid-20B, it is pretty much the same but with Noromaid-13b v0.3 instead of v0.1.1 and with a higher weight for Noromaid since 0.2 and 0.3 have improved a lot.

I used v0.3 since it was the last to use Alpaca as to not break anything.

While there arent perhaps as much point in merging smarter or better instruction following models i belive the extra parameters do add improvement.

There is a lot of promise in the MOE models but for now i just want a stable, go to 20b model.

Quants

EXL2: 6bpw, 3bpw

GGUF: Q3_K_M - Q4_K_M - Q5_K_M

Recipe:

Prompt template:

I have been using Undi/Ikaris SillyTavern presets for Noromaid: Context template, Instruct template.

Alpaca:

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

### Instruction:
{prompt}

### Input:
{input}

### Response:

Contact

Kooten on discord.