LeroyDyer/Mixtral_AI_Cyber_3.1

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using LeroyDyer/Mixtral_AI_Cyber_3.0 as a base.

Models Merged

The following models were included in the merge:

• berkeley-nest/Starling-LM-7B-alpha
• teknium/OpenHermes-2.5-Mistral-7B
• cognitivecomputations/dolphin-2.2.1-mistral-7b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: berkeley-nest/Starling-LM-7B-alpha
    parameters:
      density: [0.87, 0.721, 0.451] # density gradient
      weight: 0.876
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.232
      weight: [0.36, 0.3, 0.437, 0.76] # weight gradient
  - model: cognitivecomputations/dolphin-2.2.1-mistral-7b
    parameters:
      density: 0.475
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: LeroyDyer/Mixtral_AI_Cyber_3.0
parameters:
  normalize: true
  int8_mask: true
dtype: float16