Upload folder using huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- lesubra/merge-test
|
8 |
+
- piotr25691/thea-3b-25r
|
9 |
+
---
|
10 |
+
|
11 |
+
# ECE-EIFFEL.ia-3B
|
12 |
+
|
13 |
+
ECE-EIFFEL.ia-3B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [lesubra/merge-test](https://huggingface.co/lesubra/merge-test)
|
15 |
+
* [piotr25691/thea-3b-25r](https://huggingface.co/piotr25691/thea-3b-25r)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
slices:
|
21 |
+
- sources:
|
22 |
+
- model: lesubra/merge-test
|
23 |
+
layer_range: [0, 32]
|
24 |
+
- model: piotr25691/thea-3b-25r
|
25 |
+
layer_range: [0, 32]
|
26 |
+
merge_method: slerp
|
27 |
+
base_model: lesubra/merge-test
|
28 |
+
parameters:
|
29 |
+
t:
|
30 |
+
- filter: self_attn
|
31 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
32 |
+
- filter: mlp
|
33 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
34 |
+
- value: 0.5
|
35 |
+
dtype: bfloat16
|
36 |
+
|
37 |
+
```
|