solidrust/KatyTestHistorical-SultrySilicon-7B-V2

SultrySilicon-7B-V2

• Original Mergekit config: KatyTestHistorical/SultrySilicon-7B-V2
• Model Author: KatyTheCutie

Model Summary

Experimental 7B RP focused model - Feedback appreciated!

(V2 is a bit more sultry and lewd)

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• maywell/PiVoT-0.1-Starling-LM-RP
• senseable/WestLake-7B-v2
• CalderaAI/Naberius-7B
• cgato/Thespis-Mistral-7b-v0.7
• NeverSleep/Noromaid-7B-0.4-DPO
• SanjiWatsuki/Silicon-Maid-7B
• lemonilia/AshhLimaRP-Mistral-7B
• NurtureAI/neural-chat-7b-v3-16k

Configuration

The following YAML configuration was used to produce this model:

merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: NeverSleep/Noromaid-7B-0.4-DPO
    parameters:
      weight: 0.37
  - model: lemonilia/AshhLimaRP-Mistral-7B
    parameters:
      weight: 0.29
  - model: NurtureAI/neural-chat-7b-v3-16k
    parameters:
      weight: 0.23
  - model: cgato/Thespis-Mistral-7b-v0.7
    parameters:
      weight: 0.23
  - model: CalderaAI/Naberius-7B
    parameters:
      weight: 0.15
  - model: SanjiWatsuki/Silicon-Maid-7B
    parameters:
      weight: 0.25
  - model: senseable/WestLake-7B-v2
    parameters:
      weight: 0.27
  - model: maywell/PiVoT-0.1-Starling-LM-RP
    parameters:
      weight: 0.27
dtype: float16