Upload folder using huggingface_hub
Browse files- README.md +7 -11
- mergekit_config.yml +4 -9
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
- gradientai/Llama-3-8B-Instruct-262k
|
4 |
- Nitral-AI/Echidna-7b-128k
|
|
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
@@ -15,11 +15,12 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
15 |
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
-
This model was merged using the [
|
19 |
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
|
|
23 |
* [gradientai/Llama-3-8B-Instruct-262k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k)
|
24 |
|
25 |
### Configuration
|
@@ -29,16 +30,11 @@ The following YAML configuration was used to produce this model:
|
|
29 |
```yaml
|
30 |
models:
|
31 |
- model: Nitral-AI/Echidna-7b-128k
|
32 |
-
|
|
|
33 |
- model: gradientai/Llama-3-8B-Instruct-262k
|
34 |
parameters:
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
merge_method: dare_ties
|
39 |
-
base_model: Nitral-AI/Echidna-7b-128k
|
40 |
-
parameters:
|
41 |
-
normalize: false
|
42 |
-
int8_mask: true
|
43 |
dtype: float16
|
44 |
```
|
|
|
1 |
---
|
2 |
base_model:
|
|
|
3 |
- Nitral-AI/Echidna-7b-128k
|
4 |
+
- gradientai/Llama-3-8B-Instruct-262k
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
|
|
15 |
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
+
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
19 |
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
+
* [Nitral-AI/Echidna-7b-128k](https://huggingface.co/Nitral-AI/Echidna-7b-128k)
|
24 |
* [gradientai/Llama-3-8B-Instruct-262k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k)
|
25 |
|
26 |
### Configuration
|
|
|
30 |
```yaml
|
31 |
models:
|
32 |
- model: Nitral-AI/Echidna-7b-128k
|
33 |
+
parameters:
|
34 |
+
weight: 1.0
|
35 |
- model: gradientai/Llama-3-8B-Instruct-262k
|
36 |
parameters:
|
37 |
+
weight: 0.1
|
38 |
+
merge_method: linear
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
dtype: float16
|
40 |
```
|
mergekit_config.yml
CHANGED
@@ -1,14 +1,9 @@
|
|
1 |
models:
|
2 |
- model: Nitral-AI/Echidna-7b-128k
|
3 |
-
|
|
|
4 |
- model: gradientai/Llama-3-8B-Instruct-262k
|
5 |
parameters:
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
merge_method: dare_ties
|
10 |
-
base_model: Nitral-AI/Echidna-7b-128k
|
11 |
-
parameters:
|
12 |
-
normalize: false
|
13 |
-
int8_mask: true
|
14 |
dtype: float16
|
|
|
1 |
models:
|
2 |
- model: Nitral-AI/Echidna-7b-128k
|
3 |
+
parameters:
|
4 |
+
weight: 1.0
|
5 |
- model: gradientai/Llama-3-8B-Instruct-262k
|
6 |
parameters:
|
7 |
+
weight: 0.1
|
8 |
+
merge_method: linear
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
dtype: float16
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9886332840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebfd77390cc40bb438f7d3e409c6d4418af926448ed183e4f08f7064f8991e03
|
3 |
size 9886332840
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4597164888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:763a81a352a8e1e661ee6074285a6c81a41504ff62f6091a33f1dab3d170ef2b
|
3 |
size 4597164888
|