RichardErkhov/CorticalStack_-_neurotic-crown-clown-7b-ties-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

neurotic-crown-clown-7b-ties - GGUF

• —Model creator: https://huggingface.co/CorticalStack/
• —Original model: https://huggingface.co/CorticalStack/neurotic-crown-clown-7b-ties/

Original model description: --- license: apache-2.0 tags:

• —merge
• —mergekit
• —mlabonne/AlphaMonarch-7B
• —mlabonne/NeuralMonarch-7B
• —bardsai/jaskier-7b-dpo-v5.6 ---

neurotic-crown-clown-7B-ties

[image]

neurotic-crown-clown-7B-ties is a TRIM, ELECT SIGN & MERGE (TIES) merge of the following models using mergekit:

• —mlabonne/NeuralMonarch-7B
• —mlabonne/AlphaMonarch-7B
• —bardsai/jaskier-7b-dpo-v5.6

See the paper TIES-Merging: Resolving Interference When Merging Models for more on the method.

🧩 Configuration

models:
  - model: mlabonne/NeuralMonarch-7B
    # no parameters necessary for base model
  - model: mlabonne/AlphaMonarch-7B
    parameters:
      density: 0.5
      weight: 0.5
  - model: bardsai/jaskier-7b-dpo-v5.6
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: mlabonne/NeuralMonarch-7B
parameters:
  normalize: true
dtype: float16