QuantFactory/MN-RocinanteCelestar-12B-GGUF

This is quantized version of rityak/MN-RocinanteCelestar-12B created using llama.cpp

Original Model Card

merge

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 nothingiisreal/MN-12B-Celeste-V1.9 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nothingiisreal/MN-12B-Celeste-V1.9
  - model: nothingiisreal/MN-12B-Starcannon-v3
    parameters:
      density: 0.50
      weight: 0.50
  - model: TheDrummer/Rocinante-12B-v1
    parameters:
      density: 0.50
      weight: 0.50
merge_method: dare_ties
base_model: nothingiisreal/MN-12B-Celeste-V1.9
parameters:
  normalize: false
  int8_mask: true
dtype: float32
out_dtype: bfloat16