mav23's picture
Upload folder using huggingface_hub
ba068f7 verified
|
raw
history blame
1.9 kB
---
base_model:
- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1
- qwen/Qwen2.5-14b
- v000000/Qwen2.5-Lumen-14B
- arcee-ai/SuperNova-Medius
library_name: transformers
tags:
- mergekit
- merge
---
# Celestial Harmony 14b v1.0 Experimental 10/16
*In candlelight, as time unwinds... I find myself lost in your eyes... In midnight tolls, as darkness folds... I see your tears when we say goodbye... Watching stars as we drift on by... A touch, a glance, fly away.... Will our paths converge 'neath the sun?... A silent desire in melody sung.... In your memory, a whispered song....
A seed of hope where we belong~*
Listen to the song on Youtube: https://www.youtube.com/watch?v=kdV4K17KqAE&t=22s
Yet Another merge, this one for AuriAetherwiing, at their request. I like it, so try it out?
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 della_linear merge method using [qwen/Qwen2.5-14b](https://huggingface.co/qwen/Qwen2.5-14b) as a base.
### Models Merged
The following models were included in the merge:
* [EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1)
* [v000000/Qwen2.5-Lumen-14B](https://huggingface.co/v000000/Qwen2.5-Lumen-14B)
* [arcee-ai/SuperNova-Medius](https://huggingface.co/arcee-ai/SuperNova-Medius)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: arcee-ai/SuperNova-Medius
parameters:
weight: 0.3
density: 0.3
- model: v000000/Qwen2.5-Lumen-14B
parameters:
weight: 0.1
density: 0.3
- model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1
parameters:
weight: 0.4
density: 0.5
merge_method: della_linear
base_model: qwen/Qwen2.5-14b
parameters:
epsilon: 0.05
lambda: 1
merge_method: della_linear
dtype: bfloat16
```