Upload folder using huggingface_hub
Browse files- README.md +15 -15
- mergekit_config.yml +14 -13
- model-00001-of-00001.safetensors +1 -1
README.md
CHANGED
|
@@ -15,12 +15,11 @@ 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 |
-
* [abc88767/2c75](https://huggingface.co/abc88767/2c75)
|
| 24 |
* [rwh/s1_1712781243](https://huggingface.co/rwh/s1_1712781243)
|
| 25 |
|
| 26 |
### Configuration
|
|
@@ -29,21 +28,22 @@ The following YAML configuration was used to produce this model:
|
|
| 29 |
|
| 30 |
```yaml
|
| 31 |
|
| 32 |
-
|
| 33 |
-
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
base_model: abc88767/2c75
|
| 40 |
parameters:
|
| 41 |
-
|
| 42 |
-
- filter: self_attn
|
| 43 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
| 44 |
-
- filter: mlp
|
| 45 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
| 46 |
-
- value: 0.5
|
| 47 |
dtype: bfloat16
|
| 48 |
|
|
|
|
| 49 |
```
|
|
|
|
| 15 |
## Merge Details
|
| 16 |
### Merge Method
|
| 17 |
|
| 18 |
+
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [abc88767/2c75](https://huggingface.co/abc88767/2c75) as a base.
|
| 19 |
|
| 20 |
### Models Merged
|
| 21 |
|
| 22 |
The following models were included in the merge:
|
|
|
|
| 23 |
* [rwh/s1_1712781243](https://huggingface.co/rwh/s1_1712781243)
|
| 24 |
|
| 25 |
### Configuration
|
|
|
|
| 28 |
|
| 29 |
```yaml
|
| 30 |
|
| 31 |
+
models:
|
| 32 |
+
- model: abc88767/2c75
|
| 33 |
+
# no parameters necessary for base model
|
| 34 |
+
- model: abc88767/2c75
|
| 35 |
+
parameters:
|
| 36 |
+
density: 0.5
|
| 37 |
+
weight: 0.5
|
| 38 |
+
- model: rwh/s1_1712781243
|
| 39 |
+
parameters:
|
| 40 |
+
density: 0.5
|
| 41 |
+
weight: 0.3
|
| 42 |
+
merge_method: ties
|
| 43 |
base_model: abc88767/2c75
|
| 44 |
parameters:
|
| 45 |
+
normalize: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
dtype: bfloat16
|
| 47 |
|
| 48 |
+
|
| 49 |
```
|
mergekit_config.yml
CHANGED
|
@@ -1,17 +1,18 @@
|
|
| 1 |
|
| 2 |
-
|
| 3 |
-
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
base_model: abc88767/2c75
|
| 10 |
parameters:
|
| 11 |
-
|
| 12 |
-
- filter: self_attn
|
| 13 |
-
value: [0, 0.5, 0.3, 0.7, 1]
|
| 14 |
-
- filter: mlp
|
| 15 |
-
value: [1, 0.5, 0.7, 0.3, 0]
|
| 16 |
-
- value: 0.5
|
| 17 |
dtype: bfloat16
|
|
|
|
|
|
| 1 |
|
| 2 |
+
models:
|
| 3 |
+
- model: abc88767/2c75
|
| 4 |
+
# no parameters necessary for base model
|
| 5 |
+
- model: abc88767/2c75
|
| 6 |
+
parameters:
|
| 7 |
+
density: 0.5
|
| 8 |
+
weight: 0.5
|
| 9 |
+
- model: rwh/s1_1712781243
|
| 10 |
+
parameters:
|
| 11 |
+
density: 0.5
|
| 12 |
+
weight: 0.3
|
| 13 |
+
merge_method: ties
|
| 14 |
base_model: abc88767/2c75
|
| 15 |
parameters:
|
| 16 |
+
normalize: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
dtype: bfloat16
|
| 18 |
+
|
model-00001-of-00001.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3289069520
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc06da6673c61351a2a8895c6d9220531c36275c9e455d2dd25478168d0d2090
|
| 3 |
size 3289069520
|