Triangle104/HermesMarkle-Valiant-3B

merge

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

Merge Details

Credit to NousResearch, TroyDoesAI & ValiantLabs for models in merge.

Author Note: This model does appear to have a tendency to hallucinate, so probably best not to use this version for real-world info.

Merge Method

This model was merged using the TIES merge method using NousResearch/Hermes-3-Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

• ValiantLabs/Llama3.2-3B-ShiningValiant2
• TroyDoesAI/BlackSheep-Llama3.2-3B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Hermes-3-Llama-3.2-3B
    #no parameters necessary for base model
  - model: TroyDoesAI/BlackSheep-Llama3.2-3B
    parameters:
      density: 0.5
      weight: 0.5
  - model: ValiantLabs/Llama3.2-3B-ShiningValiant2
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: NousResearch/Hermes-3-Llama-3.2-3B
parameters:
  normalize: true
  int8_mask: true
dtype: float16