Lewdiculous/Elly_7B-GGUF-IQ-Imatrix

This repository hosts GGUF-IQ-Imatrix quants for jeiku/Elly_7B.

This model is highly experimental.

Quants:

    quantization_options = [
        "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", "Q5_K_S",
        "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
    ]

Oringinal model card:

Elly

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using SanjiWatsuki/Sonya-7B as a base.

Models Merged

The following models were included in the merge:

• MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1
• cognitivecomputations/dolphin-2.6-mistral-7b

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: SanjiWatsuki/Sonya-7B
parameters:
  normalize: true
models:
  - model: SanjiWatsuki/Sonya-7B
    parameters:
      weight: 1
  - model: cognitivecomputations/dolphin-2.6-mistral-7b
    parameters:
      weight: 1
  - model: MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1
    parameters:
      weight: 1
dtype: float16