Azazelle/Bianca-7b

Basic-Sanity

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

Merge Details

Merge Method

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

Models Merged

The following models were included in the merge:

• jan-hq/supermario-slerp-v3
• Endevor/InfinityRP-v1-7B
• Nexusflow/Starling-LM-7B-beta
• NeverSleep/Noromaid-7B-0.4-DPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Nexusflow/Starling-LM-7B-beta # Reasoning | OpenChat
    parameters:
      weight: 0.6
      density: 0.7
  - model: jan-hq/supermario-slerp-v3 # Reasoning | ChatML
    parameters:
      weight: 0.3
      density: 0.5
  - model: Endevor/InfinityRP-v1-7B # Roleplay | Alpaca
    parameters:
      weight: 0.3
      density: 0.5
  - model: NeverSleep/Noromaid-7B-0.4-DPO # Roleplay | ChatML
    parameters:
      weight: 0.2
      density: 0.4
merge_method: rescaled_sample
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16