Commit
•
b6281ea
1
Parent(s):
31b2f99
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
base_model:
|
| 5 |
+
- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1
|
| 6 |
+
- qwen/Qwen2.5-14b
|
| 7 |
+
- v000000/Qwen2.5-Lumen-14B
|
| 8 |
+
- arcee-ai/SuperNova-Medius
|
| 9 |
+
library_name: transformers
|
| 10 |
+
tags:
|
| 11 |
+
- mergekit
|
| 12 |
+
- merge
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
[](https://hf.co/QuantFactory)
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
# QuantFactory/Celestial-Harmony-14b-v1.0-Experimental-1016-GGUF
|
| 21 |
+
This is quantized version of [ProdeusUnity/Celestial-Harmony-14b-v1.0-Experimental-1016](https://huggingface.co/ProdeusUnity/Celestial-Harmony-14b-v1.0-Experimental-1016) created using llama.cpp
|
| 22 |
+
|
| 23 |
+
# Original Model Card
|
| 24 |
+
|
| 25 |
+
# Celestial Harmony 14b v1.0 Experimental 10/16
|
| 26 |
+
|
| 27 |
+
*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....
|
| 28 |
+
A seed of hope where we belong~*
|
| 29 |
+
|
| 30 |
+
Listen to the song on Youtube: https://www.youtube.com/watch?v=kdV4K17KqAE&t=22s
|
| 31 |
+
|
| 32 |
+
Yet Another merge, this one for AuriAetherwiing, at their request. I like it, so try it out?
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 36 |
+
|
| 37 |
+
## Merge Details
|
| 38 |
+
### Merge Method
|
| 39 |
+
|
| 40 |
+
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.
|
| 41 |
+
|
| 42 |
+
### Models Merged
|
| 43 |
+
|
| 44 |
+
The following models were included in the merge:
|
| 45 |
+
* [EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1)
|
| 46 |
+
* [v000000/Qwen2.5-Lumen-14B](https://huggingface.co/v000000/Qwen2.5-Lumen-14B)
|
| 47 |
+
* [arcee-ai/SuperNova-Medius](https://huggingface.co/arcee-ai/SuperNova-Medius)
|
| 48 |
+
|
| 49 |
+
### Configuration
|
| 50 |
+
|
| 51 |
+
The following YAML configuration was used to produce this model:
|
| 52 |
+
|
| 53 |
+
```yaml
|
| 54 |
+
models:
|
| 55 |
+
- model: arcee-ai/SuperNova-Medius
|
| 56 |
+
parameters:
|
| 57 |
+
weight: 0.3
|
| 58 |
+
density: 0.3
|
| 59 |
+
- model: v000000/Qwen2.5-Lumen-14B
|
| 60 |
+
parameters:
|
| 61 |
+
weight: 0.1
|
| 62 |
+
density: 0.3
|
| 63 |
+
- model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1
|
| 64 |
+
parameters:
|
| 65 |
+
weight: 0.4
|
| 66 |
+
density: 0.5
|
| 67 |
+
merge_method: della_linear
|
| 68 |
+
base_model: qwen/Qwen2.5-14b
|
| 69 |
+
parameters:
|
| 70 |
+
epsilon: 0.05
|
| 71 |
+
lambda: 1
|
| 72 |
+
merge_method: della_linear
|
| 73 |
+
dtype: bfloat16
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
```
|
| 77 |
+
|