Edit
Browse files
README.md
CHANGED
@@ -13,45 +13,4 @@ tags:
|
|
13 |
- mergekit
|
14 |
- merge
|
15 |
|
16 |
-
---
|
17 |
-
# merge
|
18 |
-
|
19 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
20 |
-
|
21 |
-
## Merge Details
|
22 |
-
### Merge Method
|
23 |
-
|
24 |
-
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5](https://huggingface.co/TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5) as a base.
|
25 |
-
|
26 |
-
### Models Merged
|
27 |
-
|
28 |
-
The following models were included in the merge:
|
29 |
-
* [ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3](https://huggingface.co/ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3)
|
30 |
-
* [AiCloser/Qwen2.5-32B-AGI](https://huggingface.co/AiCloser/Qwen2.5-32B-AGI)
|
31 |
-
* [nbeerbower/Dumpling-Qwen2.5-32B-v2](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2)
|
32 |
-
* [rinna/qwen2.5-bakeneko-32b-instruct](https://huggingface.co/rinna/qwen2.5-bakeneko-32b-instruct)
|
33 |
-
* [Sao10K/32B-Qwen2.5-Kunou-v1](https://huggingface.co/Sao10K/32B-Qwen2.5-Kunou-v1)
|
34 |
-
* [allura-org/Qwen2.5-32b-RP-Ink](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink)
|
35 |
-
* [EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2)
|
36 |
-
|
37 |
-
### Configuration
|
38 |
-
|
39 |
-
The following YAML configuration was used to produce this model:
|
40 |
-
|
41 |
-
```yaml
|
42 |
-
base_model: TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5
|
43 |
-
merge_method: sce
|
44 |
-
dype: float32
|
45 |
-
out_dtype: bfloat16
|
46 |
-
tokenizer_source: Qwen/Qwen2.5-32B
|
47 |
-
Parameters:
|
48 |
-
select_topk: 0.16
|
49 |
-
models:
|
50 |
-
- model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
|
51 |
-
- model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
|
52 |
-
- model: allura-org/Qwen2.5-32b-RP-Ink
|
53 |
-
- model: Sao10K/32B-Qwen2.5-Kunou-v1
|
54 |
-
- model: nbeerbower/Dumpling-Qwen2.5-32B-v2
|
55 |
-
- model: rinna/qwen2.5-bakeneko-32b-instruct
|
56 |
-
- model: AiCloser/Qwen2.5-32B-AGI
|
57 |
-
```
|
|
|
13 |
- mergekit
|
14 |
- merge
|
15 |
|
16 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|