README.md

metadata

base_model:
  - Hasnonname/Qwen2.5-14B-Wheatear-v0
  - Hasnonname/Qwen2.5-14B-Kestrel-v0
library_name: transformers
tags:
  - mergekit
  - merge

Qwen2.5-14B-Kebab-v0

methodology taken from Aletheia v1

hyperparams from Sugarquill v1

dataset consists of creative writing, multiturn RP, and some general assistant tasks

quants available here: Qwen2.5-14B-Kebab-v0-GGUF

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Hasnonname/Qwen2.5-14B-Wheatear-v0
• Hasnonname/Qwen2.5-14B-Kestrel-v0

Configuration

The following YAML configuration was used to produce this model:

base_model: Hasnonname/Qwen2.5-14B-Wheatear-v0
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - value: 0.7
slices:
- sources:
  - layer_range: [0, 48]
    model: Hasnonname/Qwen2.5-14B-Kestrel-v0
  - layer_range: [0, 48]
    model: Hasnonname/Qwen2.5-14B-Wheatear-v0