Queen-2.5-14B-aka / README.md
AIgotahole's picture
Upload folder using huggingface_hub
ca04316 verified
|
raw
history blame
1.55 kB
---
base_model:
- sometimesanotion/Qwenvergence-14B-v13-Prose-DS
- Sao10K/14B-Qwen2.5-Kunou-v1
- deepcogito/cogito-v1-preview-qwen-14B
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Model Breadcrumbs](https://arxiv.org/abs/2312.06795) merge method using [Sao10K/14B-Qwen2.5-Kunou-v1](https://huggingface.co/Sao10K/14B-Qwen2.5-Kunou-v1) as a base.
### Models Merged
The following models were included in the merge:
* [sometimesanotion/Qwenvergence-14B-v13-Prose-DS](https://huggingface.co/sometimesanotion/Qwenvergence-14B-v13-Prose-DS)
* [deepcogito/cogito-v1-preview-qwen-14B](https://huggingface.co/deepcogito/cogito-v1-preview-qwen-14B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Sao10K/14B-Qwen2.5-Kunou-v1
- model: sometimesanotion/Qwenvergence-14B-v13-Prose-DS
parameters:
density: [0.16, 0.26, 0.36, 0.46, 0.56, 0.46, 0.36, 0.26, 0.16]
weight: [0.166, 0.496, 0.496, 0.166, 0.166, 0.496, 0.496, 0.166]
- model: deepcogito/cogito-v1-preview-qwen-14B
parameters:
density: [0.56, 0.46, 0.36, 0.26, 0.16, 0.26, 0.36, 0.46, 0.56]
weight: [0.496, 0.166, 0.166, 0.496, 0.496, 0.166, 0.166, 0.496]
merge_method: breadcrumbs
base_model: Sao10K/14B-Qwen2.5-Kunou-v1
parameters:
gamma: 0.06
lambda: 0.96
tokenizer_source: base
dtype: bfloat16
```