Update README.md
Browse files
README.md
CHANGED
@@ -1,26 +1,25 @@
|
|
1 |
---
|
2 |
-
base_model:
|
|
|
|
|
|
|
|
|
3 |
library_name: transformers
|
4 |
tags:
|
5 |
- mergekit
|
6 |
- merge
|
7 |
-
|
|
|
|
|
8 |
---
|
|
|
9 |
# Yanfei-v2-Qwen3-32B
|
10 |
|
11 |
-
|
12 |
-
|
13 |
-
## Merge Details
|
14 |
-
### Merge Method
|
15 |
-
|
16 |
-
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using /home/nbeerbower/AI/nvidia/text-generation-webui/user_data/models/nbeerbower_Yanfei-Qwen3-32B as a base.
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
21 |
-
* /home/nbeerbower/AI/nvidia/text-generation-webui/user_data/models/Menghua-Qwen3-32B-merged
|
22 |
-
* /home/nbeerbower/AI/nvidia/text-generation-webui/user_data/models/huihui-ai_Qwen3-32B-abliterated
|
23 |
-
* /home/nbeerbower/AI/nvidia/text-generation-webui/user_data/models/Zhiming-Qwen3-32B-merged
|
24 |
|
25 |
### Configuration
|
26 |
|
@@ -28,20 +27,20 @@ The following YAML configuration was used to produce this model:
|
|
28 |
|
29 |
```yaml
|
30 |
models:
|
31 |
-
- model:
|
32 |
parameters:
|
33 |
weight: 1
|
34 |
density: 1
|
35 |
-
- model:
|
36 |
parameters:
|
37 |
weight: 1
|
38 |
density: 1
|
39 |
-
- model:
|
40 |
parameters:
|
41 |
weight: 1
|
42 |
density: 1
|
43 |
merge_method: ties
|
44 |
-
base_model:
|
45 |
parameters:
|
46 |
weight: 1
|
47 |
density: 1
|
@@ -50,4 +49,4 @@ parameters:
|
|
50 |
dtype: bfloat16
|
51 |
|
52 |
|
53 |
-
```
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- nbeerbower/Yanfei-Qwen3-32B
|
4 |
+
- huihui-ai/Qwen3-32B-abliterated
|
5 |
+
- nbeerbower/Zhiming-Qwen3-32B-lora
|
6 |
+
- nbeerbower/Menghua-Qwen3-32B-lora
|
7 |
library_name: transformers
|
8 |
tags:
|
9 |
- mergekit
|
10 |
- merge
|
11 |
+
license: apache-2.0
|
12 |
+
datasets:
|
13 |
+
- nbeerbower/YanfeiMix-DPO
|
14 |
---
|
15 |
+

|
16 |
# Yanfei-v2-Qwen3-32B
|
17 |
|
18 |
+
A repair of Yanfei-Qwen-32B by [TIES](https://arxiv.org/abs/2306.01708) merging huihui-ai/Qwen3-32B-abliterated, Zhiming-Qwen3-32B, and Menghua-Qwen3-32B using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
+
## Sponsorship
|
21 |
|
22 |
+
This model was made possible with compute support from [Nectar AI](https://nectar.ai). Thank you! ❤️
|
|
|
|
|
|
|
23 |
|
24 |
### Configuration
|
25 |
|
|
|
27 |
|
28 |
```yaml
|
29 |
models:
|
30 |
+
- model: ./Zhiming-Qwen3-32B-merged
|
31 |
parameters:
|
32 |
weight: 1
|
33 |
density: 1
|
34 |
+
- model: ./Menghua-Qwen3-32B-merged
|
35 |
parameters:
|
36 |
weight: 1
|
37 |
density: 1
|
38 |
+
- model: huihui-ai/Qwen3-32B-abliterated
|
39 |
parameters:
|
40 |
weight: 1
|
41 |
density: 1
|
42 |
merge_method: ties
|
43 |
+
base_model: nbeerbower/Yanfei-Qwen3-32B
|
44 |
parameters:
|
45 |
weight: 1
|
46 |
density: 1
|
|
|
49 |
dtype: bfloat16
|
50 |
|
51 |
|
52 |
+
```
|