Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2.5-Math-1.5B-Instruct
|
4 |
+
- WiroAI/WiroAI-Finance-Qwen-1.5B
|
5 |
+
- Qwen/Qwen2.5-1.5B-Instruct
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- mergekit
|
9 |
+
- merge
|
10 |
+
|
11 |
+
---
|
12 |
+
# merge
|
13 |
+
|
14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
+
|
16 |
+
## Merge Details
|
17 |
+
### Merge Method
|
18 |
+
|
19 |
+
This model was merged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) as a base.
|
20 |
+
|
21 |
+
### Models Merged
|
22 |
+
|
23 |
+
The following models were included in the merge:
|
24 |
+
* [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct)
|
25 |
+
* [WiroAI/WiroAI-Finance-Qwen-1.5B](https://huggingface.co/WiroAI/WiroAI-Finance-Qwen-1.5B)
|
26 |
+
|
27 |
+
### Configuration
|
28 |
+
|
29 |
+
The following YAML configuration was used to produce this model:
|
30 |
+
|
31 |
+
```yaml
|
32 |
+
|
33 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
34 |
+
|
35 |
+
models:
|
36 |
+
- model: WiroAI/WiroAI-Finance-Qwen-1.5B
|
37 |
+
parameters:
|
38 |
+
weight: 1.0
|
39 |
+
- model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
40 |
+
parameters:
|
41 |
+
weight: 1.0
|
42 |
+
|
43 |
+
merge_method: task_arithmetic
|
44 |
+
parameters:
|
45 |
+
lambda: 1.0
|
46 |
+
dtype: float16
|
47 |
+
|
48 |
+
```
|