Upload folder using huggingface_hub
Browse files- README.md +5 -5
- config.json +1 -1
- mergekit_config.yml +3 -3
- model-00001-of-00001.safetensors +1 -1
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- coffiee/g12
|
| 4 |
-
-
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mergekit
|
|
@@ -21,7 +21,7 @@ This model was merged using the SLERP merge method.
|
|
| 21 |
|
| 22 |
The following models were included in the merge:
|
| 23 |
* [coffiee/g12](https://huggingface.co/coffiee/g12)
|
| 24 |
-
* [
|
| 25 |
|
| 26 |
### Configuration
|
| 27 |
|
|
@@ -33,17 +33,17 @@ slices:
|
|
| 33 |
- sources:
|
| 34 |
- model: coffiee/g12
|
| 35 |
layer_range: [0, 18]
|
| 36 |
-
- model:
|
| 37 |
layer_range: [0, 18]
|
| 38 |
merge_method: slerp
|
| 39 |
-
base_model: coffiee/
|
| 40 |
parameters:
|
| 41 |
t:
|
| 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.
|
| 47 |
dtype: bfloat16
|
| 48 |
|
| 49 |
```
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- coffiee/g12
|
| 4 |
+
- Sumail/Barista18
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mergekit
|
|
|
|
| 21 |
|
| 22 |
The following models were included in the merge:
|
| 23 |
* [coffiee/g12](https://huggingface.co/coffiee/g12)
|
| 24 |
+
* [Sumail/Barista18](https://huggingface.co/Sumail/Barista18)
|
| 25 |
|
| 26 |
### Configuration
|
| 27 |
|
|
|
|
| 33 |
- sources:
|
| 34 |
- model: coffiee/g12
|
| 35 |
layer_range: [0, 18]
|
| 36 |
+
- model: Sumail/Barista18
|
| 37 |
layer_range: [0, 18]
|
| 38 |
merge_method: slerp
|
| 39 |
+
base_model: coffiee/g12
|
| 40 |
parameters:
|
| 41 |
t:
|
| 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: 0.8
|
| 47 |
dtype: bfloat16
|
| 48 |
|
| 49 |
```
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "coffiee/
|
| 3 |
"architectures": [
|
| 4 |
"GemmaForCausalLM"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "coffiee/g12",
|
| 3 |
"architectures": [
|
| 4 |
"GemmaForCausalLM"
|
| 5 |
],
|
mergekit_config.yml
CHANGED
|
@@ -3,15 +3,15 @@ slices:
|
|
| 3 |
- sources:
|
| 4 |
- model: coffiee/g12
|
| 5 |
layer_range: [0, 18]
|
| 6 |
-
- model:
|
| 7 |
layer_range: [0, 18]
|
| 8 |
merge_method: slerp
|
| 9 |
-
base_model: coffiee/
|
| 10 |
parameters:
|
| 11 |
t:
|
| 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.
|
| 17 |
dtype: bfloat16
|
|
|
|
| 3 |
- sources:
|
| 4 |
- model: coffiee/g12
|
| 5 |
layer_range: [0, 18]
|
| 6 |
+
- model: Sumail/Barista18
|
| 7 |
layer_range: [0, 18]
|
| 8 |
merge_method: slerp
|
| 9 |
+
base_model: coffiee/g12
|
| 10 |
parameters:
|
| 11 |
t:
|
| 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: 0.8
|
| 17 |
dtype: bfloat16
|
model-00001-of-00001.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5012363856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2192330efe01629a89e1cf937efc33af64194fcbca54c5b43464031373580cff
|
| 3 |
size 5012363856
|