Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-4

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 Sakalti/Saka-14B as a base.

Models Merged

The following models were included in the merge:

• sometimesanotion/Qwenvergence-14B-v12-Prose-DS
• Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-2
• sometimesanotion/Lamarck-14B-v0.7
• Sakalti/ultiima-14B-v0.2
• Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-3

Configuration

The following YAML configuration was used to produce this model:

name: NQLSG-Qwen2.5-14B-MegaFusion-TIES-4
models:
  - model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-2
  - model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-3
  - model: Sakalti/ultiima-14B-v0.2
  - model: sometimesanotion/Qwenvergence-14B-v12-Prose-DS
  - model: sometimesanotion/Lamarck-14B-v0.7
  - model: Sakalti/Saka-14B
base_model: Sakalti/Saka-14B
chat_template: auto
dtype: bfloat16
merge_method: ties
parameters:
  weight: 1.0
  density: 1.0
  normalize: true
  int8_mask: true
tokenizer:
  source: union