RichardErkhov/mergekit-community_-_mergekit-ties-knfdutf-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-ties-knfdutf - GGUF

• —Model creator: https://huggingface.co/mergekit-community/
• —Original model: https://huggingface.co/mergekit-community/mergekit-ties-knfdutf/

Original model description: --- base_model:

• —teknium/Hermes-Trismegistus-Mistral-7B
• —mlabonne/NeuralDaredevil-8B-abliterated
• —eldogbbhed/NeuralMonarchCoderPearlBeagle library_name: transformers tags:
• —mergekit
• —merge

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 eldogbbhed/NeuralMonarchCoderPearlBeagle as a base.

Models Merged

The following models were included in the merge:

• —teknium/Hermes-Trismegistus-Mistral-7B
• —mlabonne/NeuralDaredevil-8B-abliterated

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: eldogbbhed/NeuralMonarchCoderPearlBeagle
    #no parameters necessary for base model
  - model: mlabonne/NeuralDaredevil-8B-abliterated
    parameters:
      density: 0.5
      weight: 0.5
  - model: teknium/Hermes-Trismegistus-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: eldogbbhed/NeuralMonarchCoderPearlBeagle
parameters:
  normalize: false
  int8_mask: true
dtype: float16