RichardErkhov/ockerman0_-_MN-12B-Starcannon-v5.5-unofficial-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MN-12B-Starcannon-v5.5-unofficial - GGUF

• —Model creator: https://huggingface.co/ockerman0/
• —Original model: https://huggingface.co/ockerman0/MN-12B-Starcannon-v5.5-unofficial/

Original model description: --- base_model:

• —nothingiisreal/MN-12B-Starcannon-v3 library_name: transformers tags:
• —mergekit
• —merge

Unofficial continuation of aetherwiing's "Starcannon" series

By request, I made this merge of v3 and v5. It doesn't seem majorly dissimilar from v5, but it does seem to act slightly differently.

static quants at: https://huggingface.co/mradermacher/MN-12B-Starcannon-v5.5-unofficial-GGUF

imatrix quants at: https://huggingface.co/mradermacher/MN-12B-Starcannon-v5.5-unofficial-i1-GGUF

mergedmodel

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 nothingiisreal/MN-12B-Starcannon-v3 as a base.

Models Merged

The following models were included in the merge:

• —/home/ciaran/Documents/Quantisingmodels/testmerges/MN-12B-Starcannon-v5-unofficial/

Configuration

The following YAML configuration was used to produce this model:

models:
    - model: /home/ciaran/Documents/Quantisingmodels/testmerges/MN-12B-Starcannon-v5-unofficial/
      parameters:
        density: 0.25
        weight: 0.4
    - model: nothingiisreal/MN-12B-Starcannon-v3
      parameters:
        density: 0.75
        weight: 0.6

merge_method: ties
base_model: nothingiisreal/MN-12B-Starcannon-v3
parameters:
    normalize: true
    int8_mask: true
dtype: bfloat16