Netrve's picture
Update README.md
019a1c1
metadata
base_model:
  - SanjiWatsuki/Silicon-Maid-7B
  - SanjiWatsuki/Loyal-Macaroni-Maid-7B
tags:
  - mergekit
  - merge
  - merge
  - not-for-all-audiences
  - nsfw
license: cc-by-4.0
language:
  - en

Loyal-Silicon-Maid-7B

This is a merge of pre-trained language models created using mergekit.

I liked both Silicon-Maid and Loyal-Macaroni-Maid by SanjiWatsuki, but was looking for a middle ground, so I made my first merge using both. Let me know how it runs for you and what your results or issues are, this is my first attempt so it might be rough.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using SanjiWatsuki/Loyal-Macaroni-Maid-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: SanjiWatsuki/Loyal-Macaroni-Maid-7B
  - model: SanjiWatsuki/Silicon-Maid-7B
    parameters:
      weight: 0.4
      density: 0.8
merge_method: dare_ties
base_model: SanjiWatsuki/Loyal-Macaroni-Maid-7B
parameters:
  int8_mask: true
dtype: bfloat16

Prompt Template (Alpaca)

  • Important Note: The limit of the context length is 8192 tokens.
  • Credits: Taken from original card by SanjiWatsuki

I found the best SillyTavern results from using the Noromaid template but please try other templates! Let me know if you find anything good.

SillyTavern config files: Context, Instruct.

Additionally, here is my highly recommended Text Completion preset. You can tweak this by adjusting temperature up or dropping min p to boost creativity or raise min p to increase stability. You shouldn't need to touch anything else!

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

### Instruction:
{prompt}

### Response: