merged-secret-hermes/README.md

base_model, library_name, tags

base_model	library_name	tags
NousResearch/Hermes-2-Theta-Llama-3-8B e12ex2/Foundation-Sec-8B-Instruct-heretic NousResearch/Meta-Llama-3-8B-Instruct	transformers	mergekit merge

merged-secret-hermes

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 NousResearch/Meta-Llama-3-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• NousResearch/Hermes-2-Theta-Llama-3-8B
• e12ex2/Foundation-Sec-8B-Instruct-heretic

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: e12ex2/Foundation-Sec-8B-Instruct-heretic
    parameters:
      density: 0.5
      weight: 0.6
  - model: NousResearch/Hermes-2-Theta-Llama-3-8B
    parameters:
      density: 0.5
      weight: 0.4
merge_method: ties
base_model: NousResearch/Meta-Llama-3-8B-Instruct
tokenizer_source: base
parameters:
  normalize: true
  int8_mask: true
dtype: float16