Upload README (2).md
Browse files- README (2).md +66 -0
README (2).md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
|
4 |
+
- senseable/WestLake-7B-v2
|
5 |
+
- S-miguel/The-Trinity-Coder-7B
|
6 |
+
- yam-peleg/Experiment26-7B
|
7 |
+
- InferenceIllusionist/Excalibur-7b-DPO
|
8 |
+
- Kukedlc/Jupiter-k-7B-slerp
|
9 |
+
library_name: transformers
|
10 |
+
tags:
|
11 |
+
- mergekit
|
12 |
+
- merge
|
13 |
+
|
14 |
+
---
|
15 |
+
# Jett-w26
|
16 |
+
|
17 |
+
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/643eab4f05a395e2b1c727e3/cXC_xRZ2fQX2CSZI-9qJT.webp)
|
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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B) as a base.
|
25 |
+
|
26 |
+
### Models Merged
|
27 |
+
|
28 |
+
The following models were included in the merge:
|
29 |
+
* [chihoonlee10/T3Q-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3Q-Mistral-Orca-Math-DPO)
|
30 |
+
* [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
|
31 |
+
* [S-miguel/The-Trinity-Coder-7B](https://huggingface.co/S-miguel/The-Trinity-Coder-7B)
|
32 |
+
* [InferenceIllusionist/Excalibur-7b-DPO](https://huggingface.co/InferenceIllusionist/Excalibur-7b-DPO)
|
33 |
+
* [Kukedlc/Jupiter-k-7B-slerp](https://huggingface.co/Kukedlc/Jupiter-k-7B-slerp)
|
34 |
+
|
35 |
+
### Configuration
|
36 |
+
|
37 |
+
The following YAML configuration was used to produce this model:
|
38 |
+
|
39 |
+
```yaml
|
40 |
+
models:
|
41 |
+
- model: yam-peleg/Experiment26-7B
|
42 |
+
# No parameters necessary for base model
|
43 |
+
- model: Kukedlc/Jupiter-k-7B-slerp
|
44 |
+
parameters:
|
45 |
+
density: 0.58
|
46 |
+
weight: 0.25
|
47 |
+
- model: S-miguel/The-Trinity-Coder-7B
|
48 |
+
parameters:
|
49 |
+
density: 0.6
|
50 |
+
weight: 0.20
|
51 |
+
- model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
|
52 |
+
parameters:
|
53 |
+
density: 0.6
|
54 |
+
weight: 0.20
|
55 |
+
- model: senseable/WestLake-7B-v2
|
56 |
+
parameters:
|
57 |
+
density: 0.56
|
58 |
+
weight: 0.20
|
59 |
+
- model: InferenceIllusionist/Excalibur-7b-DPO
|
60 |
+
parameters:
|
61 |
+
density: 0.58
|
62 |
+
weight: 0.15
|
63 |
+
merge_method: dare_ties
|
64 |
+
base_model: yam-peleg/Experiment26-7B
|
65 |
+
dtype: bfloat16
|
66 |
+
```
|